From 6e8ba494d87d05cba49224d2068dd313190adbd0 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Wed, 4 Dec 2024 20:37:45 +0100 Subject: kbuild/btf: Propagate CONFIG_WERROR to resolve_btfids MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use CONFIG_WERROR to also fail on warnings emitted by resolve_btfids. Allow the CI bots to prevent the introduction of new warnings. Signed-off-by: Thomas Weißschuh Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20241204-resolve_btfids-v3-2-e6a279a74cfd@weissschuh.net --- scripts/link-vmlinux.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index d853ddb3b28c..56a077d204cf 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -283,7 +283,11 @@ vmlinux_link vmlinux # fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF; then info BTFIDS vmlinux - ${RESOLVE_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 -- cgit v1.2.3 From d9339496729f1471b8dc326face17c4cf108b027 Mon Sep 17 00:00:00 2001 From: Akira Yokosawa Date: Tue, 10 Dec 2024 20:04:15 +0900 Subject: scripts/kernel-doc: Get -export option working again Since commit cdd30ebb1b9f ("module: Convert symbol namespace to string literal"), exported symbols marked by EXPORT_SYMBOL_NS(_GPL) are ignored by "kernel-doc -export" in fresh build of "make htmldocs". This is because regex in the perl script for those markers fails to match the new signatures: - EXPORT_SYMBOL_NS(symbol, "ns"); - EXPORT_SYMBOL_NS_GPL(symbol, "ns"); Update the regex so that it matches quoted string. Note: Escape sequence of \w is good for C identifiers, but can be too strict for quoted strings. Instead, use \S, which matches any non-whitespace character, for compatibility with possible extension of namespace convention in the future [1]. Fixes: cdd30ebb1b9f ("module: Convert symbol namespace to string literal") Link: https://lore.kernel.org/CAK7LNATMufXP0EA6QUE9hBkZMa6vJO6ZiaYuak2AhOrd2nSVKQ@mail.gmail.com/ [1] Signed-off-by: Akira Yokosawa Cc: Masahiro Yamada Tested-by: Randy Dunlap Acked-by: Randy Dunlap Signed-off-by: Jonathan Corbet Link: https://lore.kernel.org/r/e5c43f36-45cd-49f4-b7b8-ff342df3c7a4@gmail.com --- scripts/kernel-doc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/kernel-doc b/scripts/kernel-doc index f66070176ba3..4ee843d3600e 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -267,7 +267,7 @@ 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*\(\s*(\w+)\s*,\s*\w+\)\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; -- cgit v1.2.3 From 41d7ea30494cc0dde3e124a75ce0add93f988ba9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Dec 2024 12:27:12 -0800 Subject: lib: packing: add pack_fields() and unpack_fields() This is new API which caters to the following requirements: - Pack or unpack a large number of fields to/from a buffer with a small code footprint. The current alternative is to open-code a large number of calls to pack() and unpack(), or to use packing() to reduce that number to half. But packing() is not const-correct. - Use unpacked numbers stored in variables smaller than u64. This reduces the rodata footprint of the stored field arrays. - Perform error checking at compile time, rather than runtime, and return void from the API functions. Because the C preprocessor can't generate variable length code (loops), this is a bit tricky to do with macros. To handle this, implement macros which sanity check the packed field definitions based on their size. Finally, a single macro with a chain of __builtin_choose_expr() is used to select the appropriate macros. We enforce the use of ascending or descending order to avoid O(N^2) scaling when checking for overlap. Note that the macros are written with care to ensure that the compilers can correctly evaluate the resulting code at compile time. In particular, care was taken with avoiding too many nested statement expressions. Nested statement expressions trip up some compilers, especially when passing down variables created in previous statement expressions. There are two key design choices intended to keep the overall macro code size small. First, the definition of each CHECK_PACKED_FIELDS_N macro is implemented recursively, by calling the N-1 macro. This avoids needing the code to repeat multiple times. Second, the CHECK_PACKED_FIELD macro enforces that the fields in the array are sorted in order. This allows checking for overlap only with neighboring fields, rather than the general overlap case where each field would need to be checked against other fields. The overlap checks use the first two fields to determine the order of the remaining fields, thus allowing either ascending or descending order. This enables drivers the flexibility to keep the fields ordered in which ever order most naturally fits their hardware design and its associated documentation. The CHECK_PACKED_FIELDS macro is directly called from within pack_fields and unpack_fields, ensuring that all drivers using the API receive the benefits of the compile-time checks. Users do not need to directly call any of the macros directly. The CHECK_PACKED_FIELDS and its helper macros CHECK_PACKED_FIELDS_(0..50) are generated using a simple C program in scripts/gen_packed_field_checks.c This program can be compiled on demand and executed to generate the macro code in include/linux/packing.h. This will aid in the event that a driver needs more than 50 fields. The generator can be updated with a new size, and used to update the packing.h header file. In practice, the ice driver will need to support 27 fields, and the sja1105 driver will need to support 0 fields. This on-demand generation avoids the need to modify Kbuild. We do not anticipate the maximum number of fields to grow very often. - Reduced rodata footprint for the storage of the packed field arrays. To that end, we have struct packed_field_u8 and packed_field_u16, which define the fields with the associated type. More can be added as needed (unlikely for now). On these types, the same generic pack_fields() and unpack_fields() API can be used, thanks to the new C11 _Generic() selection feature, which can call pack_fields_u8() or pack_fields_16(), depending on the type of the "fields" array - a simplistic form of polymorphism. It is evaluated at compile time which function will actually be called. Over time, packing() is expected to be completely replaced either with pack() or with pack_fields(). Signed-off-by: Vladimir Oltean Co-developed-by: Jacob Keller Signed-off-by: Jacob Keller Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20241210-packing-pack-fields-and-ice-implementation-v10-3-ee56a47479ac@intel.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + Makefile | 4 + include/linux/packing.h | 425 ++++++++++++++++++++++++++++++++++++++ lib/packing.c | 153 ++++++++++++++ lib/packing_test.c | 61 ++++++ scripts/.gitignore | 1 + scripts/Makefile | 2 +- scripts/gen_packed_field_checks.c | 37 ++++ 8 files changed, 683 insertions(+), 1 deletion(-) create mode 100644 scripts/gen_packed_field_checks.c (limited to 'scripts') diff --git a/MAINTAINERS b/MAINTAINERS index af35519be320..15cf366c0aec 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17644,6 +17644,7 @@ F: Documentation/core-api/packing.rst F: include/linux/packing.h F: lib/packing.c F: lib/packing_test.c +F: scripts/gen_packed_field_checks.c PADATA PARALLEL EXECUTION MECHANISM M: Steffen Klassert diff --git a/Makefile b/Makefile index 93ab62cef244..9a9fd5504ae8 100644 --- a/Makefile +++ b/Makefile @@ -1367,6 +1367,10 @@ PHONY += scripts_unifdef scripts_unifdef: scripts_basic $(Q)$(MAKE) $(build)=scripts scripts/unifdef +PHONY += scripts_gen_packed_field_checks +scripts_gen_packed_field_checks: scripts_basic + $(Q)$(MAKE) $(build)=scripts scripts/gen_packed_field_checks + # --------------------------------------------------------------------------- # Install diff --git a/include/linux/packing.h b/include/linux/packing.h index 5d36dcd06f60..0589d70bbe04 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -8,6 +8,83 @@ #include #include +#define GEN_PACKED_FIELD_STRUCT(__type) \ + struct packed_field_ ## __type { \ + __type startbit; \ + __type endbit; \ + __type offset; \ + __type size; \ + } + +/* struct packed_field_u8. Use with bit offsets < 256, buffers < 32B and + * unpacked structures < 256B. + */ +GEN_PACKED_FIELD_STRUCT(u8); + +/* struct packed_field_u16. Use with bit offsets < 65536, buffers < 8KB and + * unpacked structures < 64KB. + */ +GEN_PACKED_FIELD_STRUCT(u16); + +#define PACKED_FIELD(start, end, struct_name, struct_field) \ +{ \ + (start), \ + (end), \ + offsetof(struct_name, struct_field), \ + sizeof_field(struct_name, struct_field), \ +} + +#define CHECK_PACKED_FIELD_OVERLAP(fields, index1, index2) ({ \ + typeof(&(fields)[0]) __f = (fields); \ + typeof(__f[0]) _f1 = __f[index1]; typeof(__f[0]) _f2 = __f[index2]; \ + const bool _ascending = __f[0].startbit < __f[1].startbit; \ + BUILD_BUG_ON_MSG(_ascending && _f1.startbit >= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks ascending order"); \ + BUILD_BUG_ON_MSG(!_ascending && _f1.startbit <= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks descending order"); \ + BUILD_BUG_ON_MSG(max(_f1.endbit, _f2.endbit) <= \ + min(_f1.startbit, _f2.startbit), \ + __stringify(fields) " field " __stringify(index2) \ + " overlaps with previous field"); \ +}) + +#define CHECK_PACKED_FIELD(fields, index) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(_f[0]) __f = _f[index]; \ + BUILD_BUG_ON_MSG(__f.startbit < __f.endbit, \ + __stringify(fields) " field " __stringify(index) \ + " start bit must not be smaller than end bit"); \ + BUILD_BUG_ON_MSG(__f.size != 1 && __f.size != 2 && \ + __f.size != 4 && __f.size != 8, \ + __stringify(fields) " field " __stringify(index) \ + " has unsupported unpacked storage size"); \ + BUILD_BUG_ON_MSG(__f.startbit - __f.endbit >= BITS_PER_BYTE * __f.size, \ + __stringify(fields) " field " __stringify(index) \ + " exceeds unpacked storage size"); \ + __builtin_choose_expr(index != 0, \ + CHECK_PACKED_FIELD_OVERLAP(fields, index - 1, index), \ + 1); \ +}) + +/* Note that the packed fields may be either in ascending or descending order. + * Thus, we must check that both the first and last field wit within the + * packed buffer size. + */ +#define CHECK_PACKED_FIELDS_SIZE(fields, pbuflen) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(pbuflen) _len = (pbuflen); \ + const size_t num_fields = ARRAY_SIZE(fields); \ + BUILD_BUG_ON_MSG(!__builtin_constant_p(_len), \ + __stringify(fields) " pbuflen " __stringify(pbuflen) \ + " must be a compile time constant"); \ + BUILD_BUG_ON_MSG(_f[0].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " first field exceeds packed buffer size"); \ + BUILD_BUG_ON_MSG(_f[num_fields - 1].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " last field exceeds packed buffer size"); \ +}) + #define QUIRK_MSB_ON_THE_RIGHT BIT(0) #define QUIRK_LITTLE_ENDIAN BIT(1) #define QUIRK_LSW32_IS_FIRST BIT(2) @@ -26,4 +103,352 @@ int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, size_t pbuflen, u8 quirks); +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +/* Do not hand-edit the following packed field check macros! + * + * They are generated using scripts/gen_packed_field_checks.c, which may be + * built via "make scripts_gen_packed_field_checks". If larger macro sizes are + * needed in the future, please use this program to re-generate the macros and + * insert them here. + */ + +#define CHECK_PACKED_FIELDS_1(fields) \ + CHECK_PACKED_FIELD(fields, 0) + +#define CHECK_PACKED_FIELDS_2(fields) do { \ + CHECK_PACKED_FIELDS_1(fields); \ + CHECK_PACKED_FIELD(fields, 1); \ +} while (0) + +#define CHECK_PACKED_FIELDS_3(fields) do { \ + CHECK_PACKED_FIELDS_2(fields); \ + CHECK_PACKED_FIELD(fields, 2); \ +} while (0) + +#define CHECK_PACKED_FIELDS_4(fields) do { \ + CHECK_PACKED_FIELDS_3(fields); \ + CHECK_PACKED_FIELD(fields, 3); \ +} while (0) + +#define CHECK_PACKED_FIELDS_5(fields) do { \ + CHECK_PACKED_FIELDS_4(fields); \ + CHECK_PACKED_FIELD(fields, 4); \ +} while (0) + +#define CHECK_PACKED_FIELDS_6(fields) do { \ + CHECK_PACKED_FIELDS_5(fields); \ + CHECK_PACKED_FIELD(fields, 5); \ +} while (0) + +#define CHECK_PACKED_FIELDS_7(fields) do { \ + CHECK_PACKED_FIELDS_6(fields); \ + CHECK_PACKED_FIELD(fields, 6); \ +} while (0) + +#define CHECK_PACKED_FIELDS_8(fields) do { \ + CHECK_PACKED_FIELDS_7(fields); \ + CHECK_PACKED_FIELD(fields, 7); \ +} while (0) + +#define CHECK_PACKED_FIELDS_9(fields) do { \ + CHECK_PACKED_FIELDS_8(fields); \ + CHECK_PACKED_FIELD(fields, 8); \ +} while (0) + +#define CHECK_PACKED_FIELDS_10(fields) do { \ + CHECK_PACKED_FIELDS_9(fields); \ + CHECK_PACKED_FIELD(fields, 9); \ +} while (0) + +#define CHECK_PACKED_FIELDS_11(fields) do { \ + CHECK_PACKED_FIELDS_10(fields); \ + CHECK_PACKED_FIELD(fields, 10); \ +} while (0) + +#define CHECK_PACKED_FIELDS_12(fields) do { \ + CHECK_PACKED_FIELDS_11(fields); \ + CHECK_PACKED_FIELD(fields, 11); \ +} while (0) + +#define CHECK_PACKED_FIELDS_13(fields) do { \ + CHECK_PACKED_FIELDS_12(fields); \ + CHECK_PACKED_FIELD(fields, 12); \ +} while (0) + +#define CHECK_PACKED_FIELDS_14(fields) do { \ + CHECK_PACKED_FIELDS_13(fields); \ + CHECK_PACKED_FIELD(fields, 13); \ +} while (0) + +#define CHECK_PACKED_FIELDS_15(fields) do { \ + CHECK_PACKED_FIELDS_14(fields); \ + CHECK_PACKED_FIELD(fields, 14); \ +} while (0) + +#define CHECK_PACKED_FIELDS_16(fields) do { \ + CHECK_PACKED_FIELDS_15(fields); \ + CHECK_PACKED_FIELD(fields, 15); \ +} while (0) + +#define CHECK_PACKED_FIELDS_17(fields) do { \ + CHECK_PACKED_FIELDS_16(fields); \ + CHECK_PACKED_FIELD(fields, 16); \ +} while (0) + +#define CHECK_PACKED_FIELDS_18(fields) do { \ + CHECK_PACKED_FIELDS_17(fields); \ + CHECK_PACKED_FIELD(fields, 17); \ +} while (0) + +#define CHECK_PACKED_FIELDS_19(fields) do { \ + CHECK_PACKED_FIELDS_18(fields); \ + CHECK_PACKED_FIELD(fields, 18); \ +} while (0) + +#define CHECK_PACKED_FIELDS_20(fields) do { \ + CHECK_PACKED_FIELDS_19(fields); \ + CHECK_PACKED_FIELD(fields, 19); \ +} while (0) + +#define CHECK_PACKED_FIELDS_21(fields) do { \ + CHECK_PACKED_FIELDS_20(fields); \ + CHECK_PACKED_FIELD(fields, 20); \ +} while (0) + +#define CHECK_PACKED_FIELDS_22(fields) do { \ + CHECK_PACKED_FIELDS_21(fields); \ + CHECK_PACKED_FIELD(fields, 21); \ +} while (0) + +#define CHECK_PACKED_FIELDS_23(fields) do { \ + CHECK_PACKED_FIELDS_22(fields); \ + CHECK_PACKED_FIELD(fields, 22); \ +} while (0) + +#define CHECK_PACKED_FIELDS_24(fields) do { \ + CHECK_PACKED_FIELDS_23(fields); \ + CHECK_PACKED_FIELD(fields, 23); \ +} while (0) + +#define CHECK_PACKED_FIELDS_25(fields) do { \ + CHECK_PACKED_FIELDS_24(fields); \ + CHECK_PACKED_FIELD(fields, 24); \ +} while (0) + +#define CHECK_PACKED_FIELDS_26(fields) do { \ + CHECK_PACKED_FIELDS_25(fields); \ + CHECK_PACKED_FIELD(fields, 25); \ +} while (0) + +#define CHECK_PACKED_FIELDS_27(fields) do { \ + CHECK_PACKED_FIELDS_26(fields); \ + CHECK_PACKED_FIELD(fields, 26); \ +} while (0) + +#define CHECK_PACKED_FIELDS_28(fields) do { \ + CHECK_PACKED_FIELDS_27(fields); \ + CHECK_PACKED_FIELD(fields, 27); \ +} while (0) + +#define CHECK_PACKED_FIELDS_29(fields) do { \ + CHECK_PACKED_FIELDS_28(fields); \ + CHECK_PACKED_FIELD(fields, 28); \ +} while (0) + +#define CHECK_PACKED_FIELDS_30(fields) do { \ + CHECK_PACKED_FIELDS_29(fields); \ + CHECK_PACKED_FIELD(fields, 29); \ +} while (0) + +#define CHECK_PACKED_FIELDS_31(fields) do { \ + CHECK_PACKED_FIELDS_30(fields); \ + CHECK_PACKED_FIELD(fields, 30); \ +} while (0) + +#define CHECK_PACKED_FIELDS_32(fields) do { \ + CHECK_PACKED_FIELDS_31(fields); \ + CHECK_PACKED_FIELD(fields, 31); \ +} while (0) + +#define CHECK_PACKED_FIELDS_33(fields) do { \ + CHECK_PACKED_FIELDS_32(fields); \ + CHECK_PACKED_FIELD(fields, 32); \ +} while (0) + +#define CHECK_PACKED_FIELDS_34(fields) do { \ + CHECK_PACKED_FIELDS_33(fields); \ + CHECK_PACKED_FIELD(fields, 33); \ +} while (0) + +#define CHECK_PACKED_FIELDS_35(fields) do { \ + CHECK_PACKED_FIELDS_34(fields); \ + CHECK_PACKED_FIELD(fields, 34); \ +} while (0) + +#define CHECK_PACKED_FIELDS_36(fields) do { \ + CHECK_PACKED_FIELDS_35(fields); \ + CHECK_PACKED_FIELD(fields, 35); \ +} while (0) + +#define CHECK_PACKED_FIELDS_37(fields) do { \ + CHECK_PACKED_FIELDS_36(fields); \ + CHECK_PACKED_FIELD(fields, 36); \ +} while (0) + +#define CHECK_PACKED_FIELDS_38(fields) do { \ + CHECK_PACKED_FIELDS_37(fields); \ + CHECK_PACKED_FIELD(fields, 37); \ +} while (0) + +#define CHECK_PACKED_FIELDS_39(fields) do { \ + CHECK_PACKED_FIELDS_38(fields); \ + CHECK_PACKED_FIELD(fields, 38); \ +} while (0) + +#define CHECK_PACKED_FIELDS_40(fields) do { \ + CHECK_PACKED_FIELDS_39(fields); \ + CHECK_PACKED_FIELD(fields, 39); \ +} while (0) + +#define CHECK_PACKED_FIELDS_41(fields) do { \ + CHECK_PACKED_FIELDS_40(fields); \ + CHECK_PACKED_FIELD(fields, 40); \ +} while (0) + +#define CHECK_PACKED_FIELDS_42(fields) do { \ + CHECK_PACKED_FIELDS_41(fields); \ + CHECK_PACKED_FIELD(fields, 41); \ +} while (0) + +#define CHECK_PACKED_FIELDS_43(fields) do { \ + CHECK_PACKED_FIELDS_42(fields); \ + CHECK_PACKED_FIELD(fields, 42); \ +} while (0) + +#define CHECK_PACKED_FIELDS_44(fields) do { \ + CHECK_PACKED_FIELDS_43(fields); \ + CHECK_PACKED_FIELD(fields, 43); \ +} while (0) + +#define CHECK_PACKED_FIELDS_45(fields) do { \ + CHECK_PACKED_FIELDS_44(fields); \ + CHECK_PACKED_FIELD(fields, 44); \ +} while (0) + +#define CHECK_PACKED_FIELDS_46(fields) do { \ + CHECK_PACKED_FIELDS_45(fields); \ + CHECK_PACKED_FIELD(fields, 45); \ +} while (0) + +#define CHECK_PACKED_FIELDS_47(fields) do { \ + CHECK_PACKED_FIELDS_46(fields); \ + CHECK_PACKED_FIELD(fields, 46); \ +} while (0) + +#define CHECK_PACKED_FIELDS_48(fields) do { \ + CHECK_PACKED_FIELDS_47(fields); \ + CHECK_PACKED_FIELD(fields, 47); \ +} while (0) + +#define CHECK_PACKED_FIELDS_49(fields) do { \ + CHECK_PACKED_FIELDS_48(fields); \ + CHECK_PACKED_FIELD(fields, 48); \ +} while (0) + +#define CHECK_PACKED_FIELDS_50(fields) do { \ + CHECK_PACKED_FIELDS_49(fields); \ + CHECK_PACKED_FIELD(fields, 49); \ +} while (0) + +#define CHECK_PACKED_FIELDS(fields) \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 1, ({ CHECK_PACKED_FIELDS_1(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 2, ({ CHECK_PACKED_FIELDS_2(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 3, ({ CHECK_PACKED_FIELDS_3(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 4, ({ CHECK_PACKED_FIELDS_4(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 5, ({ CHECK_PACKED_FIELDS_5(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 6, ({ CHECK_PACKED_FIELDS_6(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 7, ({ CHECK_PACKED_FIELDS_7(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 8, ({ CHECK_PACKED_FIELDS_8(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 9, ({ CHECK_PACKED_FIELDS_9(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 10, ({ CHECK_PACKED_FIELDS_10(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 11, ({ CHECK_PACKED_FIELDS_11(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 12, ({ CHECK_PACKED_FIELDS_12(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 13, ({ CHECK_PACKED_FIELDS_13(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 14, ({ CHECK_PACKED_FIELDS_14(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 15, ({ CHECK_PACKED_FIELDS_15(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 16, ({ CHECK_PACKED_FIELDS_16(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 17, ({ CHECK_PACKED_FIELDS_17(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 18, ({ CHECK_PACKED_FIELDS_18(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 19, ({ CHECK_PACKED_FIELDS_19(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 20, ({ CHECK_PACKED_FIELDS_20(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 21, ({ CHECK_PACKED_FIELDS_21(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 22, ({ CHECK_PACKED_FIELDS_22(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 23, ({ CHECK_PACKED_FIELDS_23(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 24, ({ CHECK_PACKED_FIELDS_24(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 25, ({ CHECK_PACKED_FIELDS_25(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 26, ({ CHECK_PACKED_FIELDS_26(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 27, ({ CHECK_PACKED_FIELDS_27(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 28, ({ CHECK_PACKED_FIELDS_28(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 29, ({ CHECK_PACKED_FIELDS_29(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 30, ({ CHECK_PACKED_FIELDS_30(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 31, ({ CHECK_PACKED_FIELDS_31(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 32, ({ CHECK_PACKED_FIELDS_32(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 33, ({ CHECK_PACKED_FIELDS_33(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 34, ({ CHECK_PACKED_FIELDS_34(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 35, ({ CHECK_PACKED_FIELDS_35(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 36, ({ CHECK_PACKED_FIELDS_36(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 37, ({ CHECK_PACKED_FIELDS_37(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 38, ({ CHECK_PACKED_FIELDS_38(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 39, ({ CHECK_PACKED_FIELDS_39(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 40, ({ CHECK_PACKED_FIELDS_40(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 41, ({ CHECK_PACKED_FIELDS_41(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 42, ({ CHECK_PACKED_FIELDS_42(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 43, ({ CHECK_PACKED_FIELDS_43(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 44, ({ CHECK_PACKED_FIELDS_44(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 45, ({ CHECK_PACKED_FIELDS_45(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 46, ({ CHECK_PACKED_FIELDS_46(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 47, ({ CHECK_PACKED_FIELDS_47(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 48, ({ CHECK_PACKED_FIELDS_48(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 49, ({ CHECK_PACKED_FIELDS_49(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 50, ({ CHECK_PACKED_FIELDS_50(fields); }), \ + ({ BUILD_BUG_ON_MSG(1, "CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than 50."); }) \ +)))))))))))))))))))))))))))))))))))))))))))))))))) + +/* End of generated content */ + +#define pack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : pack_fields_u8, \ + const struct packed_field_u16 * : pack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + +#define unpack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : unpack_fields_u8, \ + const struct packed_field_u16 * : unpack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + #endif diff --git a/lib/packing.c b/lib/packing.c index 09a2d195b943..bb1643d9e64d 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -5,10 +5,37 @@ #include #include #include +#include #include #include #include +#define __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &(fields)[i]; \ + u64 uval; \ + \ + uval = ustruct_field_to_u64(ustruct, field->offset, field->size); \ + \ + __pack(pbuf, uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + } \ + }) + +#define __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &fields[i]; \ + u64 uval; \ + \ + __unpack(pbuf, &uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + \ + u64_to_ustruct_field(ustruct, field->offset, field->size, uval); \ + } \ + }) + /** * calculate_box_addr - Determine physical location of byte in buffer * @box: Index of byte within buffer seen as a logical big-endian big number @@ -322,4 +349,130 @@ int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, } EXPORT_SYMBOL(packing); +static u64 ustruct_field_to_u64(const void *ustruct, size_t field_offset, + size_t field_size) +{ + switch (field_size) { + case 1: + return *((u8 *)(ustruct + field_offset)); + case 2: + return *((u16 *)(ustruct + field_offset)); + case 4: + return *((u32 *)(ustruct + field_offset)); + default: + return *((u64 *)(ustruct + field_offset)); + } +} + +static void u64_to_ustruct_field(void *ustruct, size_t field_offset, + size_t field_size, u64 uval) +{ + switch (field_size) { + case 1: + *((u8 *)(ustruct + field_offset)) = uval; + break; + case 2: + *((u16 *)(ustruct + field_offset)) = uval; + break; + case 4: + *((u32 *)(ustruct + field_offset)) = uval; + break; + default: + *((u64 *)(ustruct + field_offset)) = uval; + break; + } +} + +/** + * pack_fields_u8 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definition. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u8); + +/** + * pack_fields_u16 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u16); + +/** + * unpack_fields_u8 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u8); + +/** + * unpack_fields_u16 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u16); + MODULE_DESCRIPTION("Generic bitfield packing and unpacking"); diff --git a/lib/packing_test.c b/lib/packing_test.c index b38ea43c03fd..ce3b83d33b04 100644 --- a/lib/packing_test.c +++ b/lib/packing_test.c @@ -396,9 +396,70 @@ static void packing_test_unpack(struct kunit *test) KUNIT_EXPECT_EQ(test, uval, params->uval); } +#define PACKED_BUF_SIZE 8 + +typedef struct __packed { u8 buf[PACKED_BUF_SIZE]; } packed_buf_t; + +struct test_data { + u32 field3; + u16 field2; + u16 field4; + u16 field6; + u8 field1; + u8 field5; +}; + +static const struct packed_field_u8 test_fields[] = { + PACKED_FIELD(63, 61, struct test_data, field1), + PACKED_FIELD(60, 52, struct test_data, field2), + PACKED_FIELD(51, 28, struct test_data, field3), + PACKED_FIELD(27, 14, struct test_data, field4), + PACKED_FIELD(13, 9, struct test_data, field5), + PACKED_FIELD(8, 0, struct test_data, field6), +}; + +static void packing_test_pack_fields(struct kunit *test) +{ + const struct test_data data = { + .field1 = 0x2, + .field2 = 0x100, + .field3 = 0xF00050, + .field4 = 0x7D3, + .field5 = 0x9, + .field6 = 0x10B, + }; + packed_buf_t expect = { + .buf = { 0x50, 0x0F, 0x00, 0x05, 0x01, 0xF4, 0xD3, 0x0B }, + }; + packed_buf_t buf = {}; + + pack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_MEMEQ(test, &expect, &buf, sizeof(buf)); +} + +static void packing_test_unpack_fields(struct kunit *test) +{ + const packed_buf_t buf = { + .buf = { 0x17, 0x28, 0x10, 0x19, 0x3D, 0xA9, 0x07, 0x9C }, + }; + struct test_data data = {}; + + unpack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_EQ(test, 0, data.field1); + KUNIT_EXPECT_EQ(test, 0x172, data.field2); + KUNIT_EXPECT_EQ(test, 0x810193, data.field3); + KUNIT_EXPECT_EQ(test, 0x36A4, data.field4); + KUNIT_EXPECT_EQ(test, 0x3, data.field5); + KUNIT_EXPECT_EQ(test, 0x19C, data.field6); +} + static struct kunit_case packing_test_cases[] = { KUNIT_CASE_PARAM(packing_test_pack, packing_gen_params), KUNIT_CASE_PARAM(packing_test_unpack, packing_gen_params), + KUNIT_CASE(packing_test_pack_fields), + KUNIT_CASE(packing_test_unpack_fields), {}, }; 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..546e8175e1c4 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -47,7 +47,7 @@ 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 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 +#include + +#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"); +} -- cgit v1.2.3 From 20d00cfae627f048560c46ba5849011a34515103 Mon Sep 17 00:00:00 2001 From: Przemek Kitszel Date: Mon, 16 Dec 2024 15:15:30 +0100 Subject: checkpatch: don't complain on _Generic() use Improve CamelCase recognition logic to avoid reporting on _Generic() use. Other C keywords, such as _Bool, are intentionally omitted, as those should be rather avoided in new source code. Reviewed-by: Wojciech Drewek Reviewed-by: Simon Horman Signed-off-by: Mateusz Polchlopek Acked-by: Joe Perches Signed-off-by: Przemek Kitszel Signed-off-by: Tony Nguyen --- scripts/checkpatch.pl | 2 ++ 1 file changed, 2 insertions(+) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9eed3683ad76..a2066a6c9dd8 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5843,6 +5843,8 @@ 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 variants -- cgit v1.2.3 From a34e92d2e831729f0ed5df20d15b4df419cd0ba4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 3 Dec 2024 20:14:45 +0900 Subject: kbuild: deb-pkg: add debarch for ARCH=um 'make ARCH=um bindeb-pkg' shows the following warning. $ make ARCH=um bindeb-pkg [snip] GEN debian ** ** ** WARNING ** ** ** Your architecture doesn't have its equivalent Debian userspace architecture defined! Falling back to the current host architecture (amd64). Please add support for um to ./scripts/package/mkdebian ... This commit hard-codes i386/amd64 because UML is only supported for x86. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/package/mkdebian | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'scripts') diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 4ffcc70f8e31..b038a1380b8a 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -70,6 +70,13 @@ set_debarch() { debarch=sh4$(if_enabled_echo CONFIG_CPU_BIG_ENDIAN eb) fi ;; + um) + if is_enabled CONFIG_64BIT; then + debarch=amd64 + else + debarch=i386 + fi + ;; esac if [ -z "$debarch" ]; then debarch=$(dpkg-architecture -qDEB_HOST_ARCH) -- cgit v1.2.3 From 54956567a055345d17438f08c895c68aff3f4cf2 Mon Sep 17 00:00:00 2001 From: Nicolas Schier Date: Thu, 12 Dec 2024 14:05:29 +0100 Subject: kbuild: deb-pkg: Do not install maint scripts for arch 'um' Stop installing Debian maintainer scripts when building a user-mode-linux Debian package. Debian maintainer scripts are used for e.g. requesting rebuilds of initrd, rebuilding DKMS modules and updating of grub configuration. As all of this is not relevant for UML but also may lead to failures while processing the kernel hooks, do no more install maintainer scripts for the UML package. Suggested-by: Masahiro Yamada Signed-off-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'scripts') diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..ad7aba0f268e 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -63,6 +63,12 @@ install_linux_image () { esac cp "$(${MAKE} -s -f ${srctree}/Makefile image_name)" "${pdir}/${installed_image_path}" + if [ "${ARCH}" != um ]; then + install_maint_scripts "${pdir}" + fi +} + +install_maint_scripts () { # Install the maintainer scripts # Note: hook scripts under /etc/kernel are also executed by official Debian # kernel packages, as well as kernel packages built using make-kpkg. -- cgit v1.2.3 From 9435dc77a33fa20afec7cd35ceaae5f7f42dbbe2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 13 Dec 2024 00:46:15 +0900 Subject: modpost: distinguish same module paths from different dump files Since commit 13b25489b6f8 ("kbuild: change working directory to external module directory with M="), module paths are always relative to the top of the external module tree. The module paths recorded in Module.symvers are no longer globally unique when they are passed via KBUILD_EXTRA_SYMBOLS for building other external modules, which may result in false-positive "exported twice" errors. Such errors should not occur because external modules should be able to override in-tree modules. To address this, record the dump file path in struct module and check it when searching for a module. Fixes: 13b25489b6f8 ("kbuild: change working directory to external module directory with M=") Reported-by: Jon Hunter Closes: https://lore.kernel.org/all/eb21a546-a19c-40df-b821-bbba80f19a3d@nvidia.com/ Signed-off-by: Masahiro Yamada Tested-by: Jon Hunter --- scripts/mod/modpost.c | 17 +++++++++-------- scripts/mod/modpost.h | 3 ++- 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'scripts') diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..94ee49207a45 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -155,12 +155,13 @@ char *get_line(char **stringp) /* A list of all modules we processed */ LIST_HEAD(modules); -static struct module *find_module(const char *modname) +static struct module *find_module(const char *filename, const char *modname) { struct module *mod; list_for_each_entry(mod, &modules, list) { - if (strcmp(mod->name, modname) == 0) + if (!strcmp(mod->dump_file, filename) && + !strcmp(mod->name, modname)) return mod; } return NULL; @@ -2030,10 +2031,10 @@ static void read_dump(const char *fname) continue; } - mod = find_module(modname); + mod = find_module(fname, modname); if (!mod) { mod = new_module(modname, strlen(modname)); - mod->from_dump = true; + mod->dump_file = fname; } s = sym_add_exported(symname, mod, gpl_only, namespace); sym_set_crc(s, crc); @@ -2052,7 +2053,7 @@ static void write_dump(const char *fname) struct symbol *sym; list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; list_for_each_entry(sym, &mod->exported_symbols, list) { if (trim_unused_exports && !sym->used) @@ -2076,7 +2077,7 @@ static void write_namespace_deps_files(const char *fname) list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || list_empty(&mod->missing_namespaces)) + if (mod->dump_file || list_empty(&mod->missing_namespaces)) continue; buf_printf(&ns_deps_buf, "%s.ko:", mod->name); @@ -2194,7 +2195,7 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || mod->is_vmlinux) + if (mod->dump_file || mod->is_vmlinux) continue; check_modname_len(mod); @@ -2205,7 +2206,7 @@ int main(int argc, char **argv) handle_white_list_exports(unused_exports_white_list); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; if (mod->is_vmlinux) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 49848fcbe2a1..8b72c227ebf4 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -95,14 +95,15 @@ struct module_alias { /** * struct module - represent a module (vmlinux or *.ko) * + * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases */ struct module { struct list_head list; struct list_head exported_symbols; struct list_head unresolved_symbols; + const char *dump_file; bool is_gpl_compatible; - bool from_dump; /* true if module was loaded from *.symvers */ bool is_vmlinux; bool seen; bool has_init; -- cgit v1.2.3 From 8541bf0239b8509ecc1192b2e26768a36fd9c944 Mon Sep 17 00:00:00 2001 From: Abhishek Pandit-Subedi Date: Fri, 13 Dec 2024 15:35:42 -0800 Subject: usb: typec: Only use SVID for matching altmodes Mode in struct typec_altmode is used to indicate the index of the altmode on a port, partner or plug. It is used in enter mode VDMs but doesn't make much sense for matching against altmode drivers or for matching partner to port altmodes. Signed-off-by: Abhishek Pandit-Subedi Reviewed-by: Heikki Krogerus Reviewed-by: Benson Leung Link: https://lore.kernel.org/r/20241213153543.v5.1.Ie0d37646f18461234777d88b4c3e21faed92ed4f@changeid Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 2 +- drivers/usb/typec/altmodes/nvidia.c | 2 +- drivers/usb/typec/bus.c | 6 ++---- drivers/usb/typec/class.c | 4 ++-- scripts/mod/devicetable-offsets.c | 1 - scripts/mod/file2alias.c | 9 ++------- 6 files changed, 8 insertions(+), 16 deletions(-) (limited to 'scripts') diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 2f03190a9873..3245e03d59e6 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -791,7 +791,7 @@ void dp_altmode_remove(struct typec_altmode *alt) EXPORT_SYMBOL_GPL(dp_altmode_remove); static const struct typec_device_id dp_typec_id[] = { - { USB_TYPEC_DP_SID, USB_TYPEC_DP_MODE }, + { USB_TYPEC_DP_SID }, { }, }; MODULE_DEVICE_TABLE(typec, dp_typec_id); diff --git a/drivers/usb/typec/altmodes/nvidia.c b/drivers/usb/typec/altmodes/nvidia.c index fe70b36f078f..2b77d931e494 100644 --- a/drivers/usb/typec/altmodes/nvidia.c +++ b/drivers/usb/typec/altmodes/nvidia.c @@ -24,7 +24,7 @@ static void nvidia_altmode_remove(struct typec_altmode *alt) } static const struct typec_device_id nvidia_typec_id[] = { - { USB_TYPEC_NVIDIA_VLINK_SID, TYPEC_ANY_MODE }, + { USB_TYPEC_NVIDIA_VLINK_SID }, { }, }; MODULE_DEVICE_TABLE(typec, nvidia_typec_id); diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index aa879253d3b8..ae90688d23e4 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -454,8 +454,7 @@ static int typec_match(struct device *dev, const struct device_driver *driver) const struct typec_device_id *id; for (id = drv->id_table; id->svid; id++) - if (id->svid == altmode->svid && - (id->mode == TYPEC_ANY_MODE || id->mode == altmode->mode)) + if (id->svid == altmode->svid) return 1; return 0; } @@ -470,8 +469,7 @@ static int typec_uevent(const struct device *dev, struct kobj_uevent_env *env) if (add_uevent_var(env, "MODE=%u", altmode->mode)) return -ENOMEM; - return add_uevent_var(env, "MODALIAS=typec:id%04Xm%02X", - altmode->svid, altmode->mode); + return add_uevent_var(env, "MODALIAS=typec:id%04X", altmode->svid); } static int typec_altmode_create_links(struct altmode *alt) diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 4b3047e055a3..febe453b96be 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -237,13 +237,13 @@ static int altmode_match(struct device *dev, void *data) if (!is_typec_altmode(dev)) return 0; - return ((adev->svid == id->svid) && (adev->mode == id->mode)); + return (adev->svid == id->svid); } static void typec_altmode_set_partner(struct altmode *altmode) { struct typec_altmode *adev = &altmode->adev; - struct typec_device_id id = { adev->svid, adev->mode, }; + struct typec_device_id id = { adev->svid }; struct typec_port *port = typec_altmode2port(adev); struct altmode *partner; struct device *dev; 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 5b5745f00eb3..7049c31062c6 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1221,17 +1221,12 @@ 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 */ -- cgit v1.2.3 From 7a6c355b55c051eb37cb15d191241da3aa3d6cba Mon Sep 17 00:00:00 2001 From: Mostafa Saleh Date: Mon, 23 Dec 2024 12:44:53 +0000 Subject: scripts/mksysmap: Fix escape chars '$' Commit b18b047002b7 ("kbuild: change scripts/mksysmap into sed script") changed the invocation of the script, to call sed directly without shell. That means, the current extra escape that was added in: commit ec336aa83162 ("scripts/mksysmap: Fix badly escaped '$'") for the shell is not correct any more, at the moment the stack traces for nvhe are corrupted: [ 22.840904] kvm [190]: [] __kvm_nvhe_$x.220+0x58/0x9c [ 22.842913] kvm [190]: [] __kvm_nvhe_$x.9+0x44/0x50 [ 22.844112] kvm [190]: [] __kvm_nvhe___skip_pauth_save+0x4/0x4 With this patch: [ 25.793513] kvm [192]: nVHE call trace: [ 25.794141] kvm [192]: [] __kvm_nvhe_hyp_panic+0xb0/0xf4 [ 25.796590] kvm [192]: [] __kvm_nvhe_handle_trap+0xe4/0x188 [ 25.797553] kvm [192]: [] __kvm_nvhe___skip_pauth_save+0x4/0x4 Fixes: b18b047002b7 ("kbuild: change scripts/mksysmap into sed script") Signed-off-by: Mostafa Saleh Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- scripts/mksysmap | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/mksysmap b/scripts/mksysmap index c12723a04655..3accbdb269ac 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -26,7 +26,7 @@ # (do not forget a space before each pattern) # local symbols for ARM, MIPS, etc. -/ \\$/d +/ \$/d # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d @@ -39,7 +39,7 @@ / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace -/ __kvm_nvhe_\\$/d +/ __kvm_nvhe_\$/d / __kvm_nvhe_\.L/d # lld arm/aarch64/mips thunks -- cgit v1.2.3 From bf36b4bf1b9a7a0015610e2f038ee84ddb085de2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 26 Dec 2024 00:33:35 +0900 Subject: modpost: fix the missed iteration for the max bit in do_input() This loop should iterate over the range from 'min' to 'max' inclusively. The last interation is missed. Fixes: 1d8f430c15b3 ("[PATCH] Input: add modalias support") Signed-off-by: Masahiro Yamada Tested-by: John Paul Adrian Glaubitz --- scripts/mod/file2alias.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5b5745f00eb3..ff263c285977 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -656,7 +656,7 @@ static void do_input(char *alias, for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) arr[i] = TO_NATIVE(arr[i]); - for (i = min; i < max; i++) + for (i = min; i <= max; i++) if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } -- cgit v1.2.3 From e1352d7ead2b8803689823cd4059c1ec72609ed4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 26 Dec 2024 00:33:36 +0900 Subject: modpost: refactor do_vmbus_entry() Optimize the size of guid_name[], as it only requires 1 additional byte for '\0' instead of 2. Simplify the loop by incrementing the iterator by 1 instead of 2. Remove the unnecessary TO_NATIVE() call, as the guid is represented as a byte stream. Signed-off-by: Masahiro Yamada Tested-by: John Paul Adrian Glaubitz --- scripts/mod/file2alias.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'scripts') diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index ff263c285977..2c7b76d4e8ec 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -812,15 +812,13 @@ static void do_virtio_entry(struct module *mod, void *symval) * Each byte of the guid will be represented by two hex characters * in the name. */ - static void do_vmbus_entry(struct module *mod, void *symval) { - int i; DEF_FIELD_ADDR(symval, hv_vmbus_device_id, guid); - char guid_name[(sizeof(*guid) + 1) * 2]; + char guid_name[sizeof(*guid) * 2 + 1]; - for (i = 0; i < (sizeof(*guid) * 2); i += 2) - sprintf(&guid_name[i], "%02x", TO_NATIVE((guid->b)[i/2])); + for (int i = 0; i < sizeof(*guid); i++) + sprintf(&guid_name[i * 2], "%02x", guid->b[i]); module_alias_printf(mod, false, "vmbus:%s", guid_name); } -- cgit v1.2.3 From 8fe1a63d3d99d86f1bdc034505aad6fc70424737 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 26 Dec 2024 00:33:37 +0900 Subject: modpost: work around unaligned data access error With the latest binutils, modpost fails with a bus error on some architectures such as ARM and sparc64. Since binutils commit 1f1b5e506bf0 ("bfd/ELF: restrict file alignment for object files"), the byte offset to each section (sh_offset) in relocatable ELF is no longer guaranteed to be aligned. modpost parses MODULE_DEVICE_TABLE() data structures, which are usually located in the .rodata section. If it is not properly aligned, unaligned access errors may occur. To address the issue, this commit imports the get_unaligned() helper from include/linux/unaligned.h. The get_unaligned_native() helper caters to the endianness in addition to handling the unaligned access. I slightly refactored do_pcmcia_entry() and do_input() to avoid writing back to an unaligned address. (We would need the put_unaligned() helper to do that.) The addend_*_rel() functions need similar adjustments because the .text sections are not aligned either. It seems that the .symtab, .rel.* and .rela.* sections are still aligned. Keep normal pointer access for these sections to avoid unnecessary performance costs. Reported-by: Paulo Pisati Reported-by: Matthias Klose Closes: https://sourceware.org/bugzilla/show_bug.cgi?id=32435 Reported-by: John Paul Adrian Glaubitz Closes: https://sourceware.org/bugzilla/show_bug.cgi?id=32493 Signed-off-by: Masahiro Yamada Tested-by: John Paul Adrian Glaubitz --- scripts/mod/file2alias.c | 26 +++++++++++++------------- scripts/mod/modpost.c | 24 ++++++++++++------------ scripts/mod/modpost.h | 14 ++++++++++++++ 3 files changed, 39 insertions(+), 25 deletions(-) (limited to 'scripts') diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 2c7b76d4e8ec..19ec72a69e90 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -132,7 +132,8 @@ struct devtable { * based at address m. */ #define DEF_FIELD(m, devid, f) \ - typeof(((struct devid *)0)->f) f = TO_NATIVE(*(typeof(f) *)((m) + OFF_##devid##_##f)) + typeof(((struct devid *)0)->f) f = \ + get_unaligned_native((typeof(f) *)((m) + OFF_##devid##_##f)) /* Define a variable f that holds the address of field f of struct devid * based at address m. Due to the way typeof works, for a field of type @@ -600,7 +601,7 @@ static void do_pnp_card_entry(struct module *mod, void *symval) static void do_pcmcia_entry(struct module *mod, void *symval) { char alias[256] = {}; - unsigned int i; + DEF_FIELD(symval, pcmcia_device_id, match_flags); DEF_FIELD(symval, pcmcia_device_id, manf_id); DEF_FIELD(symval, pcmcia_device_id, card_id); @@ -609,10 +610,6 @@ static void do_pcmcia_entry(struct module *mod, void *symval) DEF_FIELD(symval, pcmcia_device_id, device_no); DEF_FIELD_ADDR(symval, pcmcia_device_id, prod_id_hash); - for (i=0; i<4; i++) { - (*prod_id_hash)[i] = TO_NATIVE((*prod_id_hash)[i]); - } - ADD(alias, "m", match_flags & PCMCIA_DEV_ID_MATCH_MANF_ID, manf_id); ADD(alias, "c", match_flags & PCMCIA_DEV_ID_MATCH_CARD_ID, @@ -623,10 +620,14 @@ static void do_pcmcia_entry(struct module *mod, void *symval) function); ADD(alias, "pfn", match_flags & PCMCIA_DEV_ID_MATCH_DEVICE_NO, device_no); - ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, (*prod_id_hash)[0]); - ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, (*prod_id_hash)[1]); - ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, (*prod_id_hash)[2]); - ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, (*prod_id_hash)[3]); + ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, + get_unaligned_native(*prod_id_hash + 0)); + ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, + get_unaligned_native(*prod_id_hash + 1)); + ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, + get_unaligned_native(*prod_id_hash + 2)); + ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, + get_unaligned_native(*prod_id_hash + 3)); module_alias_printf(mod, true, "pcmcia:%s", alias); } @@ -654,10 +655,9 @@ static void do_input(char *alias, { unsigned int i; - for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) - arr[i] = TO_NATIVE(arr[i]); for (i = min; i <= max; i++) - if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) + if (get_unaligned_native(arr + i / BITS_PER_LONG) & + (1ULL << (i % BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 94ee49207a45..7ea59dc4926b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1138,9 +1138,9 @@ static Elf_Addr addend_386_rel(uint32_t *location, unsigned int r_type) { switch (r_type) { case R_386_32: - return TO_NATIVE(*location); + return get_unaligned_native(location); case R_386_PC32: - return TO_NATIVE(*location) + 4; + return get_unaligned_native(location) + 4; } return (Elf_Addr)(-1); @@ -1161,24 +1161,24 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) switch (r_type) { case R_ARM_ABS32: case R_ARM_REL32: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); return inst + sym->st_value; case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32(((inst & 0xf0000) >> 4) | (inst & 0xfff), 15); return offset + sym->st_value; case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32((inst & 0x00ffffff) << 2, 25); return offset + sym->st_value + 8; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); offset = sign_extend32(((upper & 0x000f) << 12) | ((upper & 0x0400) << 1) | ((lower & 0x7000) >> 4) | @@ -1195,8 +1195,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * imm11 = lower[10:0] * imm32 = SignExtend(S:J2:J1:imm6:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1219,8 +1219,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * I2 = NOT(J2 XOR S) * imm32 = SignExtend(S:I1:I2:imm10:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1241,7 +1241,7 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type) { uint32_t inst; - inst = TO_NATIVE(*location); + inst = get_unaligned_native(location); switch (r_type) { case R_MIPS_LO16: return inst & 0xffff; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 8b72c227ebf4..ffd0a52a606e 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -65,6 +65,20 @@ #define TO_NATIVE(x) \ (target_is_big_endian == host_is_big_endian ? x : bswap(x)) +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __attribute__((__packed__)) *__pptr = \ + (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +#define get_unaligned_native(ptr) \ +({ \ + typeof(*(ptr)) _val = get_unaligned(ptr); \ + TO_NATIVE(_val); \ +}) + #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define strstarts(str, prefix) (strncmp(str, prefix, strlen(prefix)) == 0) -- cgit v1.2.3 From da3ecf00ffc7b169b9a31a1218bbb52aa19d8df7 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sat, 21 Dec 2024 23:22:14 +0100 Subject: scripts/kernel-doc: fix identifier parsing regex John wrote: > kernel-doc gets confused by code like the following: > > /** > * define HOMA_MIN_DEFAULT_PORT - The 16-bit port space is divided into > * two nonoverlapping regions. Ports 1-32767 are reserved exclusively > * for well-defined server ports. The remaining ports are used for client > * ports; these are allocated automatically by Homa. Port 0 is reserved. > */ > #define HOMA_MIN_DEFAULT_PORT 0x8000 > > It seems to use the last "-" on the line (the one in "16-bit") rather > than the first one, so it produces the following false error message: > > homa.h:50: warning: expecting prototype for HOMA_MIN_DEFAULT_PORT - > The 16(). Prototype was for HOMA_MIN_DEFAULT_PORT() instead > > There are similar problems if there is a ":" later on the line. The problem is the regex for the identifier, which is a greedy /.*/ that matches everything up to the last - or : (i.e. $decl_end). Fix it by tightening up this regex and not matching those characters as part of the identifier. Link: https://lore.kernel.org/all/CAGXJAmzfRzE=A94NT5ETtj3bZc-=2oLg-9E5Kjh4o_-iuw1q8g@mail.gmail.com/ Reported-by: John Ousterhout Reviewed-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Vegard Nossum Signed-off-by: Jonathan Corbet Link: https://lore.kernel.org/r/20241221222214.1969823-1-vegard.nossum@oracle.com --- scripts/kernel-doc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 4ee843d3600e..e57c5e989a0a 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -2085,7 +2085,7 @@ sub process_name($$) { # 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*$decl_end$/) { + /^$decl_start$fn_type?(\w+[^-:]*)$parenthesis?\s*$decl_end$/) { $identifier = $1; $decl_type = 'function'; $identifier =~ s/^define\s+//; -- cgit v1.2.3 From 6356f18f09dc0781650c4f128ea48745fa48c415 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 5 Dec 2024 19:16:34 +0100 Subject: Align git commit ID abbreviation guidelines and checks The guidelines for git commit ID abbreviation are inconsistent: some places state to use 12 characters exactly, while other places recommend 12 characters or more. The same issue is present in the checkpatch.pl script. E.g. Documentation/dev-tools/checkpatch.rst says: **GIT_COMMIT_ID** The proper way to reference a commit id is: commit <12+ chars of sha1> ("") However, scripts/checkpatch.pl has two different checks: one warning check accepting 12 characters exactly: # Check Fixes: styles is correct Please use correct Fixes: style 'Fixes: <12 chars of sha1> (\"<title line>\")' and a second error check accepting 12-40 characters: # Check for git id commit length and improperly formed commit descriptions # A correctly formed commit description is: # commit <SHA-1 hash length 12+ chars> ("Complete commit subject") Please use git commit description style 'commit <12+ chars of sha1> Hence patches containing commit IDs with more than 12 characters are flagged by checkpatch, and sometimes rejected by maintainers or reviewers. This is becoming more important with the growth of the repository, as git may decide to use more characters in case of local conflicts. Fix this by settling on at least 12 characters, in both the documentation and in the checkpatch.pl script. Fixes: bd17e036b495bebb ("checkpatch: warn for non-standard fixes tag style") Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be> Link: https://lore.kernel.org/r/1c244040bf6ce304656e31036e5178b4b9dfb719.1733421037.git.geert+renesas@glider.be Signed-off-by: Jonathan Corbet <corbet@lwn.net> --- Documentation/process/maintainer-tip.rst | 2 +- Documentation/process/submitting-patches.rst | 8 ++++---- scripts/checkpatch.pl | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'scripts') diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst index e374b67b3277..41d5855700cd 100644 --- a/Documentation/process/maintainer-tip.rst +++ b/Documentation/process/maintainer-tip.rst @@ -270,7 +270,7 @@ Ordering of commit tags To have a uniform view of the commit tags, the tip maintainers use the following tag ordering scheme: - - Fixes: 12char-SHA1 ("sub/sys: Original subject line") + - Fixes: 12+char-SHA1 ("sub/sys: Original subject line") A Fixes tag should be added even for changes which do not need to be backported to stable kernels, i.e. when addressing a recently introduced diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index 1474c84b3ac5..816bdb037e02 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -143,10 +143,10 @@ also track such tags and take certain actions. Private bug trackers and invalid URLs are forbidden. If your patch fixes a bug in a specific commit, e.g. you found an issue using -``git bisect``, please use the 'Fixes:' tag with the first 12 characters of -the SHA-1 ID, and the one line summary. Do not split the tag across multiple -lines, tags are exempt from the "wrap at 75 columns" rule in order to simplify -parsing scripts. For example:: +``git bisect``, please use the 'Fixes:' tag with at least the first 12 +characters of the SHA-1 ID, and the one line summary. Do not split the tag +across multiple lines, tags are exempt from the "wrap at 75 columns" rule in +order to simplify parsing scripts. For example:: Fixes: 54a4f0239f2e ("KVM: MMU: make kvm_mmu_zap_page() return the number of pages it actually freed") diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9eed3683ad76..f7087dda9ac9 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3230,7 +3230,7 @@ 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 $id = "0123456789ab"; @@ -3240,7 +3240,7 @@ sub process { if ($ctitle ne $title || $tag_case || $tag_space || $id_length || $id_case || !$title_has_quotes) { 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: 'Fixes: $cid (\"$ctitle\")'\n" . $herecurr) && $fix) { $fixed[$fixlinenr] = "Fixes: $cid (\"$ctitle\")"; } -- cgit v1.2.3 From 0210d251162f4033350a94a43f95b1c39ec84a90 Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu <visitorckw@gmail.com> Date: Thu, 26 Dec 2024 22:03:32 +0800 Subject: scripts/sorttable: fix orc_sort_cmp() to maintain symmetry and transitivity The orc_sort_cmp() function, used with qsort(), previously violated the symmetry and transitivity rules required by the C standard. Specifically, when both entries are ORC_TYPE_UNDEFINED, it could result in both a < b and b < a, which breaks the required symmetry and transitivity. This can lead to undefined behavior and incorrect sorting results, potentially causing memory corruption in glibc implementations [1]. Symmetry: If x < y, then y > x. Transitivity: If x < y and y < z, then x < z. Fix the comparison logic to return 0 when both entries are ORC_TYPE_UNDEFINED, ensuring compliance with qsort() requirements. Link: https://www.qualys.com/2024/01/30/qsort.txt [1] Link: https://lkml.kernel.org/r/20241226140332.2670689-1-visitorckw@gmail.com Fixes: 57fa18994285 ("scripts/sorttable: Implement build-time ORC unwind table sorting") Fixes: fb799447ae29 ("x86,objtool: Split UNWIND_HINT_EMPTY in two") Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com> Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> Cc: <chuang@cs.nycu.edu.tw> Cc: Ingo Molnar <mingo@kernel.org> Cc: Josh Poimboeuf <jpoimboe@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shile Zhang <shile.zhang@linux.alibaba.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/sorttable.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 7bd0184380d3..a7c5445baf00 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -110,7 +110,7 @@ static inline unsigned long orc_ip(const int *ip) static int orc_sort_cmp(const void *_a, const void *_b) { - struct orc_entry *orc_a; + 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); @@ -128,6 +128,9 @@ static int orc_sort_cmp(const void *_a, const void *_b) * 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; } -- cgit v1.2.3 From 385443057f475e775fe1c66e77d4be9727f40973 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh <linux@weissschuh.net> Date: Fri, 3 Jan 2025 19:20:23 +0100 Subject: kbuild: pacman-pkg: provide versioned linux-api-headers package MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Arch Linux glibc package contains a versioned dependency on "linux-api-headers". If the linux-api-headers package provided by pacman-pkg does not specify an explicit version this dependency is not satisfied. Fix the dependency by providing an explicit version. Fixes: c8578539deba ("kbuild: add script and target to generate pacman package") Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Reviewed-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/package/PKGBUILD | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index f83493838cf9..dca706617adc 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -103,7 +103,7 @@ _package-headers() { _package-api-headers() { pkgdesc="Kernel headers sanitized for use in userspace" - provides=(linux-api-headers) + provides=(linux-api-headers="${pkgver}") conflicts=(linux-api-headers) _prologue -- cgit v1.2.3 From 28b24394c6e9a3166fcb4480cba054562526657c Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:12 -0500 Subject: scripts/sorttable: Remove unused macro defines The code of sorttable.h was copied from the recordmcount.h which defined a bunch of Elf MACROs so that they could be used between 32bit and 64bit functions. But there's several MACROs that sorttable.h does not use but was copied over. Remove them to clean up the code. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162344.128870118@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.h b/scripts/sorttable.h index a7c5445baf00..14d0c4d843e8 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -27,19 +27,10 @@ #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 @@ -52,19 +43,10 @@ # 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 @@ -76,19 +58,10 @@ # 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) -- cgit v1.2.3 From 4f48a28b37d594dab38092514a42ae9f4b781553 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:13 -0500 Subject: scripts/sorttable: Remove unused write functions The code of sorttable.h was copied from the recordmcount.h which defined various write functions for different sizes (2, 4, 8 byte lengths). But sorttable only uses the 4 byte writes. Remove the extra versions as they are not used. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162344.314385504@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 83cdb843d92f..4dcdbf7a5e26 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -68,8 +68,6 @@ 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); /* @@ -146,31 +144,11 @@ 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) -{ - put_unaligned_le16(val, x); -} - -static void w8le(uint64_t val, uint64_t *x) -{ - put_unaligned_le64(val, x); -} - /* * Move reserved section indices SHN_LORESERVE..SHN_HIRESERVE out of * the way to -256..-1, to avoid conflicting with real section @@ -277,16 +255,12 @@ static int do_file(char const *const fname, void *addr) r2 = r2le; r8 = r8le; w = wle; - w2 = w2le; - w8 = w8le; break; case ELFDATA2MSB: r = rbe; r2 = r2be; r8 = r8be; w = wbe; - w2 = w2be; - w8 = w8be; break; default: fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", -- cgit v1.2.3 From 6f2c2f93a190467cebd6ebd03feb49514fead5ca Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:14 -0500 Subject: scripts/sorttable: Remove unneeded Elf_Rel The code had references to initialize the Elf_Rel relocation tables, but it was never used. Remove it. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162344.515342233@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.h | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 14d0c4d843e8..18d07fdb2716 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -26,7 +26,6 @@ #undef Elf_Addr #undef Elf_Ehdr #undef Elf_Shdr -#undef Elf_Rel #undef Elf_Sym #undef ELF_ST_TYPE #undef uint_t @@ -42,7 +41,6 @@ # define Elf_Addr Elf64_Addr # define Elf_Ehdr Elf64_Ehdr # define Elf_Shdr Elf64_Shdr -# define Elf_Rel Elf64_Rel # define Elf_Sym Elf64_Sym # define ELF_ST_TYPE ELF64_ST_TYPE # define uint_t uint64_t @@ -57,7 +55,6 @@ # define Elf_Addr Elf32_Addr # define Elf_Ehdr Elf32_Ehdr # define Elf_Shdr Elf32_Shdr -# define Elf_Rel Elf32_Rel # define Elf_Sym Elf32_Sym # define ELF_ST_TYPE ELF32_ST_TYPE # define uint_t uint32_t @@ -248,14 +245,10 @@ static int do_sort(Elf_Ehdr *ehdr, 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; @@ -279,23 +272,15 @@ static int do_sort(Elf_Ehdr *ehdr, if (shnum == SHN_UNDEF) shnum = _r(&shdr[0].sh_size); - for (i = 0, s = shdr; s < shdr + shnum; i++, s++) { + for (s = shdr; s < shdr + shnum; s++) { idx = r(&s->sh_name); - if (!strcmp(secstrings + idx, "__ex_table")) { + 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)); @@ -397,10 +382,6 @@ static int do_sort(Elf_Ehdr *ehdr, 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); -- cgit v1.2.3 From 66990c003306c240d570b3ba274ec4f68cf18c91 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:15 -0500 Subject: scripts/sorttable: Have the ORC code use the _r() functions to read The ORC code reads the section information directly from the file. This currently works because the default read function is for 64bit little endian machines. But if for some reason that ever changes, this will break. Instead of having a surprise breakage, use the _r() functions that will read the values from the file properly. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162344.721480386@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 18d07fdb2716..58f7ab5f5644 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -299,14 +299,14 @@ static int do_sort(Elf_Ehdr *ehdr, #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; + orc_ip_size = _r(&s->sh_size); g_orc_ip_table = (int *)((void *)ehdr + - s->sh_offset); + _r(&s->sh_offset)); } if (!strcmp(secstrings + idx, ".orc_unwind")) { - orc_size = s->sh_size; + orc_size = _r(&s->sh_size); g_orc_table = (struct orc_entry *)((void *)ehdr + - s->sh_offset); + _r(&s->sh_offset)); } #endif } /* for loop */ -- cgit v1.2.3 From 7ffc0d0819f438779ed592e2e2e3576f43ce14f0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:16 -0500 Subject: scripts/sorttable: Make compare_extable() into two functions Instead of having the compare_extable() part of the sorttable.h header where it get's defined twice, since it is a very simple function, just define it twice in sorttable.c, and then it can use the proper read functions for the word size and endianess and the Elf_Addr macro can be removed from sorttable.h. Also add a micro optimization. Instead of: if (a < b) return -1; if (a > b) return 1; return 0; That can be shorten to: if (a < b) return -1; return a > b; Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162344.945299671@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 20 ++++++++++++++++++++ scripts/sorttable.h | 14 -------------- 2 files changed, 20 insertions(+), 14 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 4dcdbf7a5e26..3e2c17e91485 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -173,6 +173,26 @@ static inline unsigned int get_secindex(unsigned int shndx, return r(&symtab_shndx_start[sym_offs]); } +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; +} + /* 32 bit and 64 bit are very similar */ #include "sorttable.h" #define SORTTABLE_64 diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 58f7ab5f5644..36655ff16b39 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,7 +23,6 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef Elf_Addr #undef Elf_Ehdr #undef Elf_Shdr #undef Elf_Sym @@ -38,7 +37,6 @@ # 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_Sym Elf64_Sym @@ -52,7 +50,6 @@ # 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_Sym Elf32_Sym @@ -160,17 +157,6 @@ static void *sort_orctable(void *arg) } #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; -- cgit v1.2.3 From 157fb5b3cfd2cb5950314f926a76e567fc1921c5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:17 -0500 Subject: scripts/sorttable: Convert Elf_Ehdr to union In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions for both, replace the Elf_Ehdr macro with a union that defines both Elf64_Ehdr and Elf32_Ehdr, with field e64 for the 64bit version, and e32 for the 32bit version. Then a macro etype can be used instead to get to the proper value. This will eventually be replaced with just single functions that can handle both 32bit and 64bit ELF parsing. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162345.148224465@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 36 ++++++++++++++++++++---------------- scripts/sorttable.h | 12 ++++++------ 2 files changed, 26 insertions(+), 22 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 3e2c17e91485..67cbbfc8214d 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -64,6 +64,11 @@ #define EM_LOONGARCH 258 #endif +typedef union { + Elf32_Ehdr e32; + Elf64_Ehdr e64; +} Elf_Ehdr; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); @@ -266,10 +271,10 @@ 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; @@ -284,18 +289,18 @@ static int do_file(char const *const fname, void *addr) 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)) { + switch (r2(&ehdr->e32.e_machine)) { case EM_386: case EM_AARCH64: case EM_LOONGARCH: @@ -318,14 +323,14 @@ 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]) { + switch (ehdr->e32.e_ident[EI_CLASS]) { case ELFCLASS32: - if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) || - r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { + 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; @@ -334,20 +339,19 @@ static int do_file(char const *const fname, void *addr) 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)) { + 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; } - rc = do_sort_64(ghdr, fname, custom_sort); + rc = do_sort_64(ehdr, fname, custom_sort); } break; default: fprintf(stderr, "unrecognized ELF class %d %s\n", - ehdr->e_ident[EI_CLASS], fname); + ehdr->e32.e_ident[EI_CLASS], fname); break; } diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 36655ff16b39..be8b529498fb 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,12 +23,12 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef Elf_Ehdr #undef Elf_Shdr #undef Elf_Sym #undef ELF_ST_TYPE #undef uint_t #undef _r +#undef etype #ifdef SORTTABLE_64 # define extable_ent_size 16 @@ -37,12 +37,12 @@ # define sort_mcount_loc sort_mcount_loc_64 # define elf_mcount_loc elf_mcount_loc_64 # define do_sort do_sort_64 -# define Elf_Ehdr Elf64_Ehdr # define Elf_Shdr Elf64_Shdr # define Elf_Sym Elf64_Sym # define ELF_ST_TYPE ELF64_ST_TYPE # define uint_t uint64_t # define _r r8 +# define etype e64 #else # define extable_ent_size 8 # define compare_extable compare_extable_32 @@ -50,12 +50,12 @@ # define sort_mcount_loc sort_mcount_loc_32 # define elf_mcount_loc elf_mcount_loc_32 # define do_sort do_sort_32 -# define Elf_Ehdr Elf32_Ehdr # define Elf_Shdr Elf32_Shdr # define Elf_Sym Elf32_Sym # define ELF_ST_TYPE ELF32_ST_TYPE # define uint_t uint32_t # define _r r +# define etype e32 #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) @@ -222,7 +222,7 @@ static int do_sort(Elf_Ehdr *ehdr, table_sort_t custom_sort) { int rc = -1; - Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->e_shoff)); + Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->etype.e_shoff)); Elf_Shdr *strtab_sec = NULL; Elf_Shdr *symtab_sec = NULL; Elf_Shdr *extab_sec = NULL; @@ -249,12 +249,12 @@ static int do_sort(Elf_Ehdr *ehdr, unsigned int orc_num_entries = 0; #endif - shstrndx = r2(&ehdr->e_shstrndx); + shstrndx = r2(&ehdr->etype.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); + shnum = r2(&ehdr->etype.e_shnum); if (shnum == SHN_UNDEF) shnum = _r(&shdr[0].sh_size); -- cgit v1.2.3 From 545f6cf8f4c9a268e0bab2637f1d279679befdbf Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:18 -0500 Subject: scripts/sorttable: Replace Elf_Shdr Macro with a union In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions for both, replace the Elf_Shdr macro with a union that defines both Elf64_Shdr and Elf32_Shdr, with field e64 for the 64bit version, and e32 for the 32bit version. It can then use the macro etype to get the proper value. This will eventually be replaced with just single functions that can handle both 32bit and 64bit ELF parsing. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162345.339462681@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 10 ++++++++ scripts/sorttable.h | 74 +++++++++++++++++++++++++++++------------------------ 2 files changed, 51 insertions(+), 33 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 67cbbfc8214d..94497b8ab04c 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -69,6 +69,11 @@ typedef union { Elf64_Ehdr e64; } Elf_Ehdr; +typedef union { + Elf32_Shdr e32; + Elf64_Shdr e64; +} Elf_Shdr; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); @@ -198,6 +203,11 @@ static int compare_extable_64(const void *a, const void *b) return av > bv; } +static inline void *get_index(void *start, int entsize, int index) +{ + return start + (entsize * index); +} + /* 32 bit and 64 bit are very similar */ #include "sorttable.h" #define SORTTABLE_64 diff --git a/scripts/sorttable.h b/scripts/sorttable.h index be8b529498fb..3daf37bb6b9a 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,7 +23,6 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef Elf_Shdr #undef Elf_Sym #undef ELF_ST_TYPE #undef uint_t @@ -37,7 +36,6 @@ # define sort_mcount_loc sort_mcount_loc_64 # define elf_mcount_loc elf_mcount_loc_64 # define do_sort do_sort_64 -# define Elf_Shdr Elf64_Shdr # define Elf_Sym Elf64_Sym # define ELF_ST_TYPE ELF64_ST_TYPE # define uint_t uint64_t @@ -50,7 +48,6 @@ # define sort_mcount_loc sort_mcount_loc_32 # define elf_mcount_loc elf_mcount_loc_32 # define do_sort do_sort_32 -# define Elf_Shdr Elf32_Shdr # define Elf_Sym Elf32_Sym # define ELF_ST_TYPE ELF32_ST_TYPE # define uint_t uint32_t @@ -171,8 +168,8 @@ struct elf_mcount_loc { 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 offset = emloc->start_mcount_loc - _r(&(emloc->init_data_sec)->etype.sh_addr) + + _r(&(emloc->init_data_sec)->etype.sh_offset); uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; unsigned char *start_loc = (void *)emloc->ehdr + offset; @@ -222,10 +219,11 @@ static int do_sort(Elf_Ehdr *ehdr, table_sort_t custom_sort) { int rc = -1; - Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->etype.e_shoff)); + 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; @@ -235,7 +233,10 @@ static int do_sort(Elf_Ehdr *ehdr, const char *secstrings; const char *strtab; char *extab_image; + int sort_need_index; + int shentsize; int idx; + int i; unsigned int shnum; unsigned int shstrndx; #ifdef MCOUNT_SORT_ENABLED @@ -249,34 +250,40 @@ static int do_sort(Elf_Ehdr *ehdr, unsigned int orc_num_entries = 0; #endif + shdr_start = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->etype.e_shoff)); + shentsize = r2(&ehdr->etype.e_shentsize); + shstrndx = r2(&ehdr->etype.e_shstrndx); if (shstrndx == SHN_XINDEX) - shstrndx = r(&shdr[0].sh_link); - secstrings = (const char *)ehdr + _r(&shdr[shstrndx].sh_offset); + shstrndx = r(&shdr_start->etype.sh_link); + string_sec = get_index(shdr_start, shentsize, shstrndx); + secstrings = (const char *)ehdr + _r(&string_sec->etype.sh_offset); shnum = r2(&ehdr->etype.e_shnum); if (shnum == SHN_UNDEF) - shnum = _r(&shdr[0].sh_size); + shnum = _r(&shdr_start->etype.sh_size); + + for (i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); - for (s = shdr; s < shdr + shnum; s++) { - idx = r(&s->sh_name); + idx = r(&shdr->etype.sh_name); if (!strcmp(secstrings + idx, "__ex_table")) - extab_sec = s; + extab_sec = shdr; if (!strcmp(secstrings + idx, ".symtab")) - symtab_sec = s; + symtab_sec = shdr; if (!strcmp(secstrings + idx, ".strtab")) - strtab_sec = s; + strtab_sec = shdr; - if (r(&s->sh_type) == SHT_SYMTAB_SHNDX) + if (r(&shdr->etype.sh_type) == SHT_SYMTAB_SHNDX) symtab_shndx = (Elf32_Word *)((const char *)ehdr + - _r(&s->sh_offset)); + _r(&shdr->etype.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.init_data_sec = shdr; mstruct.start_mcount_loc = _start_mcount_loc; mstruct.stop_mcount_loc = _stop_mcount_loc; } @@ -285,14 +292,14 @@ static int do_sort(Elf_Ehdr *ehdr, #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) /* locate the ORC unwind tables */ if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { - orc_ip_size = _r(&s->sh_size); + orc_ip_size = _r(&shdr->etype.sh_size); g_orc_ip_table = (int *)((void *)ehdr + - _r(&s->sh_offset)); + _r(&shdr->etype.sh_offset)); } if (!strcmp(secstrings + idx, ".orc_unwind")) { - orc_size = _r(&s->sh_size); + orc_size = _r(&shdr->etype.sh_size); g_orc_table = (struct orc_entry *)((void *)ehdr + - _r(&s->sh_offset)); + _r(&shdr->etype.sh_offset)); } #endif } /* for loop */ @@ -355,22 +362,22 @@ static int do_sort(Elf_Ehdr *ehdr, goto out; } - extab_image = (void *)ehdr + _r(&extab_sec->sh_offset); - strtab = (const char *)ehdr + _r(&strtab_sec->sh_offset); + extab_image = (void *)ehdr + _r(&extab_sec->etype.sh_offset); + strtab = (const char *)ehdr + _r(&strtab_sec->etype.sh_offset); symtab = (const Elf_Sym *)((const char *)ehdr + - _r(&symtab_sec->sh_offset)); + _r(&symtab_sec->etype.sh_offset)); if (custom_sort) { - custom_sort(extab_image, _r(&extab_sec->sh_size)); + custom_sort(extab_image, _r(&extab_sec->etype.sh_size)); } else { - int num_entries = _r(&extab_sec->sh_size) / extable_ent_size; + int num_entries = _r(&extab_sec->etype.sh_size) / extable_ent_size; qsort(extab_image, num_entries, extable_ent_size, compare_extable); } /* 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); + for (sym = (void *)ehdr + _r(&symtab_sec->etype.sh_offset); + sym < sym + _r(&symtab_sec->etype.sh_size) / sizeof(Elf_Sym); sym++) { if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT) continue; @@ -388,13 +395,14 @@ static int do_sort(Elf_Ehdr *ehdr, goto out; } - sort_needed_sec = &shdr[get_secindex(r2(&sym->st_shndx), - sort_needed_sym - symtab, - symtab_shndx)]; + sort_need_index = get_secindex(r2(&sym->st_shndx), + sort_needed_sym - symtab, + symtab_shndx); + sort_needed_sec = get_index(shdr_start, shentsize, sort_need_index); sort_needed_loc = (void *)ehdr + - _r(&sort_needed_sec->sh_offset) + + _r(&sort_needed_sec->etype.sh_offset) + _r(&sort_needed_sym->st_value) - - _r(&sort_needed_sec->sh_addr); + _r(&sort_needed_sec->etype.sh_addr); /* extable has been sorted, clear the flag */ w(0, sort_needed_loc); -- cgit v1.2.3 From 200d015e73b4da69bcd8212a7c58695452b12bad Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:19 -0500 Subject: scripts/sorttable: Convert Elf_Sym MACRO over to a union In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions for both, replace the Elf_Sym macro with a union that defines both Elf64_Sym and Elf32_Sym, with field e64 for the 64bit version, and e32 for the 32bit version. It can then use the macro etype to get the proper value. This will eventually be replaced with just single functions that can handle both 32bit and 64bit ELF parsing. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162345.528626969@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 5 +++++ scripts/sorttable.h | 25 ++++++++++++++----------- 2 files changed, 19 insertions(+), 11 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 94497b8ab04c..57792cf2aa89 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -74,6 +74,11 @@ typedef union { Elf64_Shdr e64; } Elf_Shdr; +typedef union { + Elf32_Sym e32; + Elf64_Sym e64; +} Elf_Sym; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 3daf37bb6b9a..cd4429c8a9f4 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,7 +23,6 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef Elf_Sym #undef ELF_ST_TYPE #undef uint_t #undef _r @@ -36,7 +35,6 @@ # define sort_mcount_loc sort_mcount_loc_64 # define elf_mcount_loc elf_mcount_loc_64 # define do_sort do_sort_64 -# define Elf_Sym Elf64_Sym # define ELF_ST_TYPE ELF64_ST_TYPE # define uint_t uint64_t # define _r r8 @@ -48,7 +46,6 @@ # define sort_mcount_loc sort_mcount_loc_32 # define elf_mcount_loc elf_mcount_loc_32 # define do_sort do_sort_32 -# define Elf_Sym Elf32_Sym # define ELF_ST_TYPE ELF32_ST_TYPE # define uint_t uint32_t # define _r r @@ -230,10 +227,13 @@ static int do_sort(Elf_Ehdr *ehdr, 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; @@ -376,12 +376,15 @@ static int do_sort(Elf_Ehdr *ehdr, } /* find the flag main_extable_sort_needed */ - for (sym = (void *)ehdr + _r(&symtab_sec->etype.sh_offset); - sym < sym + _r(&symtab_sec->etype.sh_size) / sizeof(Elf_Sym); - sym++) { - if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT) + sym_start = (void *)ehdr + _r(&symtab_sec->etype.sh_offset); + sym_end = sym_start + _r(&symtab_sec->etype.sh_size); + symentsize = _r(&symtab_sec->etype.sh_entsize); + + for (sym = sym_start; (void *)sym + symentsize < sym_end; + sym = (void *)sym + symentsize) { + if (ELF_ST_TYPE(sym->etype.st_info) != STT_OBJECT) continue; - if (!strcmp(strtab + r(&sym->st_name), + if (!strcmp(strtab + r(&sym->etype.st_name), "main_extable_sort_needed")) { sort_needed_sym = sym; break; @@ -395,13 +398,13 @@ static int do_sort(Elf_Ehdr *ehdr, goto out; } - sort_need_index = get_secindex(r2(&sym->st_shndx), - sort_needed_sym - symtab, + sort_need_index = get_secindex(r2(&sym->etype.st_shndx), + ((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 + _r(&sort_needed_sec->etype.sh_offset) + - _r(&sort_needed_sym->st_value) - + _r(&sort_needed_sym->etype.st_value) - _r(&sort_needed_sec->etype.sh_addr); /* extable has been sorted, clear the flag */ -- cgit v1.2.3 From 1dfb59a228dde59ad7d99b2fa2104e90004995c7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:20 -0500 Subject: scripts/sorttable: Add helper functions for Elf_Ehdr In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions, add helper functions for Elf_Ehdr. This will create a function pointer for each helper that will get assigned to the appropriate function to handle either the 64bit or 32bit version. This also moves the _r()/r() wrappers for the Elf_Ehdr references that handle endian and size differences between the different architectures, into the helper function and out of the open code which is more error prone. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162345.736369526@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 25 +++++++++++++++++++++++++ scripts/sorttable.h | 20 ++++++++++++++++---- 2 files changed, 41 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 57792cf2aa89..5dfa734eff09 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -85,6 +85,31 @@ static uint64_t (*r8)(const uint64_t *); static void (*w)(uint32_t, uint32_t *); typedef void (*table_sort_t)(char *, int); +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); +} + +#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); \ +} + +EHDR_HALF(shentsize) +EHDR_HALF(shstrndx) +EHDR_HALF(shnum) + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap diff --git a/scripts/sorttable.h b/scripts/sorttable.h index cd4429c8a9f4..97278c973bc9 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -27,6 +27,10 @@ #undef uint_t #undef _r #undef etype +#undef ehdr_shoff +#undef ehdr_shentsize +#undef ehdr_shstrndx +#undef ehdr_shnum #ifdef SORTTABLE_64 # define extable_ent_size 16 @@ -39,6 +43,10 @@ # define uint_t uint64_t # define _r r8 # define etype e64 +# define ehdr_shoff ehdr64_shoff +# define ehdr_shentsize ehdr64_shentsize +# define ehdr_shstrndx ehdr64_shstrndx +# define ehdr_shnum ehdr64_shnum #else # define extable_ent_size 8 # define compare_extable compare_extable_32 @@ -50,6 +58,10 @@ # define uint_t uint32_t # define _r r # define etype e32 +# define ehdr_shoff ehdr32_shoff +# define ehdr_shentsize ehdr32_shentsize +# define ehdr_shstrndx ehdr32_shstrndx +# define ehdr_shnum ehdr32_shnum #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) @@ -250,16 +262,16 @@ static int do_sort(Elf_Ehdr *ehdr, unsigned int orc_num_entries = 0; #endif - shdr_start = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->etype.e_shoff)); - shentsize = r2(&ehdr->etype.e_shentsize); + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); - shstrndx = r2(&ehdr->etype.e_shstrndx); + shstrndx = ehdr_shstrndx(ehdr); if (shstrndx == SHN_XINDEX) shstrndx = r(&shdr_start->etype.sh_link); string_sec = get_index(shdr_start, shentsize, shstrndx); secstrings = (const char *)ehdr + _r(&string_sec->etype.sh_offset); - shnum = r2(&ehdr->etype.e_shnum); + shnum = ehdr_shnum(ehdr); if (shnum == SHN_UNDEF) shnum = _r(&shdr_start->etype.sh_size); -- cgit v1.2.3 From 67afb7f504400e5b4e5ff895459fbb3eb63d4450 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:21 -0500 Subject: scripts/sorttable: Add helper functions for Elf_Shdr In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions, add helper functions for Elf_Shdr. This will create a function pointer for each helper that will get assigned to the appropriate function to handle either the 64bit or 32bit version. This also moves the _r()/r() wrappers for the Elf_Shdr references that handle endian and size differences between the different architectures, into the helper function and out of the open code which is more error prone. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162345.940924221@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 42 ++++++++++++++++++++++++++++++++++ scripts/sorttable.h | 66 ++++++++++++++++++++++++++++++++++------------------- 2 files changed, 85 insertions(+), 23 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 5dfa734eff09..b2b96ff261d6 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -110,6 +110,48 @@ 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); \ +} + +#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); \ +} + +#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); \ +} + +SHDR_ADDR(addr) +SHDR_ADDR(offset) +SHDR_ADDR(size) +SHDR_ADDR(entsize) + +SHDR_WORD(link) +SHDR_WORD(name) +SHDR_WORD(type) + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 97278c973bc9..af3a5f0209a3 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -31,6 +31,13 @@ #undef ehdr_shentsize #undef ehdr_shstrndx #undef ehdr_shnum +#undef shdr_addr +#undef shdr_offset +#undef shdr_link +#undef shdr_size +#undef shdr_name +#undef shdr_type +#undef shdr_entsize #ifdef SORTTABLE_64 # define extable_ent_size 16 @@ -47,6 +54,13 @@ # define ehdr_shentsize ehdr64_shentsize # define ehdr_shstrndx ehdr64_shstrndx # define ehdr_shnum ehdr64_shnum +# define shdr_addr shdr64_addr +# define shdr_offset shdr64_offset +# define shdr_link shdr64_link +# define shdr_size shdr64_size +# define shdr_name shdr64_name +# define shdr_type shdr64_type +# define shdr_entsize shdr64_entsize #else # define extable_ent_size 8 # define compare_extable compare_extable_32 @@ -62,6 +76,13 @@ # define ehdr_shentsize ehdr32_shentsize # define ehdr_shstrndx ehdr32_shstrndx # define ehdr_shnum ehdr32_shnum +# define shdr_addr shdr32_addr +# define shdr_offset shdr32_offset +# define shdr_link shdr32_link +# define shdr_size shdr32_size +# define shdr_name shdr32_name +# define shdr_type shdr32_type +# define shdr_entsize shdr32_entsize #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) @@ -177,8 +198,8 @@ struct elf_mcount_loc { 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)->etype.sh_addr) - + _r(&(emloc->init_data_sec)->etype.sh_offset); + uint_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + + shdr_offset(emloc->init_data_sec); uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; unsigned char *start_loc = (void *)emloc->ehdr + offset; @@ -267,18 +288,18 @@ static int do_sort(Elf_Ehdr *ehdr, shstrndx = ehdr_shstrndx(ehdr); if (shstrndx == SHN_XINDEX) - shstrndx = r(&shdr_start->etype.sh_link); + shstrndx = shdr_link(shdr_start); string_sec = get_index(shdr_start, shentsize, shstrndx); - secstrings = (const char *)ehdr + _r(&string_sec->etype.sh_offset); + secstrings = (const char *)ehdr + shdr_offset(string_sec); shnum = ehdr_shnum(ehdr); if (shnum == SHN_UNDEF) - shnum = _r(&shdr_start->etype.sh_size); + shnum = shdr_size(shdr_start); for (i = 0; i < shnum; i++) { Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); - idx = r(&shdr->etype.sh_name); + idx = shdr_name(shdr); if (!strcmp(secstrings + idx, "__ex_table")) extab_sec = shdr; if (!strcmp(secstrings + idx, ".symtab")) @@ -286,9 +307,9 @@ static int do_sort(Elf_Ehdr *ehdr, if (!strcmp(secstrings + idx, ".strtab")) strtab_sec = shdr; - if (r(&shdr->etype.sh_type) == SHT_SYMTAB_SHNDX) + if (shdr_type(shdr) == SHT_SYMTAB_SHNDX) symtab_shndx = (Elf32_Word *)((const char *)ehdr + - _r(&shdr->etype.sh_offset)); + shdr_offset(shdr)); #ifdef MCOUNT_SORT_ENABLED /* locate the .init.data section in vmlinux */ @@ -304,14 +325,14 @@ static int do_sort(Elf_Ehdr *ehdr, #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) /* locate the ORC unwind tables */ if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { - orc_ip_size = _r(&shdr->etype.sh_size); + orc_ip_size = shdr_size(shdr); g_orc_ip_table = (int *)((void *)ehdr + - _r(&shdr->etype.sh_offset)); + shdr_offset(shdr)); } if (!strcmp(secstrings + idx, ".orc_unwind")) { - orc_size = _r(&shdr->etype.sh_size); + orc_size = shdr_size(shdr); g_orc_table = (struct orc_entry *)((void *)ehdr + - _r(&shdr->etype.sh_offset)); + shdr_offset(shdr)); } #endif } /* for loop */ @@ -374,23 +395,22 @@ static int do_sort(Elf_Ehdr *ehdr, goto out; } - extab_image = (void *)ehdr + _r(&extab_sec->etype.sh_offset); - strtab = (const char *)ehdr + _r(&strtab_sec->etype.sh_offset); - symtab = (const Elf_Sym *)((const char *)ehdr + - _r(&symtab_sec->etype.sh_offset)); + 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)); if (custom_sort) { - custom_sort(extab_image, _r(&extab_sec->etype.sh_size)); + custom_sort(extab_image, shdr_size(extab_sec)); } else { - int num_entries = _r(&extab_sec->etype.sh_size) / extable_ent_size; + 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 + _r(&symtab_sec->etype.sh_offset); - sym_end = sym_start + _r(&symtab_sec->etype.sh_size); - symentsize = _r(&symtab_sec->etype.sh_entsize); + 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) { @@ -415,9 +435,9 @@ static int do_sort(Elf_Ehdr *ehdr, symtab_shndx); sort_needed_sec = get_index(shdr_start, shentsize, sort_need_index); sort_needed_loc = (void *)ehdr + - _r(&sort_needed_sec->etype.sh_offset) + + shdr_offset(sort_needed_sec) + _r(&sort_needed_sym->etype.st_value) - - _r(&sort_needed_sec->etype.sh_addr); + shdr_addr(sort_needed_sec); /* extable has been sorted, clear the flag */ w(0, sort_needed_loc); -- cgit v1.2.3 From 17bed33ac12f011f4695059960e1b1d6457229a7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:22 -0500 Subject: scripts/sorttable: Add helper functions for Elf_Sym In order to remove the double #include of sorttable.h for 64 and 32 bit to create duplicate functions, add helper functions for Elf_Sym. This will create a function pointer for each helper that will get assigned to the appropriate function to handle either the 64bit or 32bit version. This also removes the last references of etype and _r() macros from the sorttable.h file as their references are now just defined in the appropriate architecture version of the helper functions. All read functions now exist in the helper functions which makes it easier to maintain, as the helper functions define the necessary architecture sizes. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162346.185740651@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ scripts/sorttable.h | 30 ++++++++++++++++-------------- 2 files changed, 63 insertions(+), 14 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index b2b96ff261d6..20615de18276 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -152,6 +152,53 @@ 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); \ +} + +#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); \ +} + +#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 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); +} + +SYM_ADDR(value) +SYM_WORD(name) +SYM_HALF(shndx) + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap diff --git a/scripts/sorttable.h b/scripts/sorttable.h index af3a5f0209a3..ef7e5161db31 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,10 +23,7 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef ELF_ST_TYPE #undef uint_t -#undef _r -#undef etype #undef ehdr_shoff #undef ehdr_shentsize #undef ehdr_shstrndx @@ -38,6 +35,10 @@ #undef shdr_name #undef shdr_type #undef shdr_entsize +#undef sym_type +#undef sym_name +#undef sym_value +#undef sym_shndx #ifdef SORTTABLE_64 # define extable_ent_size 16 @@ -46,10 +47,7 @@ # define sort_mcount_loc sort_mcount_loc_64 # define elf_mcount_loc elf_mcount_loc_64 # define do_sort do_sort_64 -# define ELF_ST_TYPE ELF64_ST_TYPE # define uint_t uint64_t -# define _r r8 -# define etype e64 # define ehdr_shoff ehdr64_shoff # define ehdr_shentsize ehdr64_shentsize # define ehdr_shstrndx ehdr64_shstrndx @@ -61,6 +59,10 @@ # define shdr_name shdr64_name # define shdr_type shdr64_type # define shdr_entsize shdr64_entsize +# define sym_type sym64_type +# define sym_name sym64_name +# define sym_value sym64_value +# define sym_shndx sym64_shndx #else # define extable_ent_size 8 # define compare_extable compare_extable_32 @@ -68,10 +70,7 @@ # define sort_mcount_loc sort_mcount_loc_32 # define elf_mcount_loc elf_mcount_loc_32 # define do_sort do_sort_32 -# define ELF_ST_TYPE ELF32_ST_TYPE # define uint_t uint32_t -# define _r r -# define etype e32 # define ehdr_shoff ehdr32_shoff # define ehdr_shentsize ehdr32_shentsize # define ehdr_shstrndx ehdr32_shstrndx @@ -83,6 +82,10 @@ # define shdr_name shdr32_name # define shdr_type shdr32_type # define shdr_entsize shdr32_entsize +# define sym_type sym32_type +# define sym_name sym32_name +# define sym_value sym32_value +# define sym_shndx sym32_shndx #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) @@ -414,9 +417,9 @@ static int do_sort(Elf_Ehdr *ehdr, for (sym = sym_start; (void *)sym + symentsize < sym_end; sym = (void *)sym + symentsize) { - if (ELF_ST_TYPE(sym->etype.st_info) != STT_OBJECT) + if (sym_type(sym) != STT_OBJECT) continue; - if (!strcmp(strtab + r(&sym->etype.st_name), + if (!strcmp(strtab + sym_name(sym), "main_extable_sort_needed")) { sort_needed_sym = sym; break; @@ -430,14 +433,13 @@ static int do_sort(Elf_Ehdr *ehdr, goto out; } - sort_need_index = get_secindex(r2(&sym->etype.st_shndx), + 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) + - _r(&sort_needed_sym->etype.st_value) - - shdr_addr(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); -- cgit v1.2.3 From 1b649e6ab8dc9188d82c64069493afe66ca0edad Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:23 -0500 Subject: scripts/sorttable: Use uint64_t for mcount sorting The mcount sorting defines uint_t to uint64_t on 64bit architectures and uint32_t on 32bit architectures. It can work with just using uint64_t as that will hold the values of both, and they are not used to point into the ELF file. sizeof(uint_t) is used for defining the size of the mcount_loc section. Instead of using a type, define long_size and use that instead. This will allow the header code to be moved into the C file as generic functions and not need to include sorttable.h twice, once for 64bit and once for 32bit. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162346.373528925@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.h b/scripts/sorttable.h index ef7e5161db31..17a8541a10d6 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -23,7 +23,6 @@ #undef sort_mcount_loc #undef elf_mcount_loc #undef do_sort -#undef uint_t #undef ehdr_shoff #undef ehdr_shentsize #undef ehdr_shstrndx @@ -39,6 +38,7 @@ #undef sym_name #undef sym_value #undef sym_shndx +#undef long_size #ifdef SORTTABLE_64 # define extable_ent_size 16 @@ -47,7 +47,6 @@ # define sort_mcount_loc sort_mcount_loc_64 # define elf_mcount_loc elf_mcount_loc_64 # define do_sort do_sort_64 -# define uint_t uint64_t # define ehdr_shoff ehdr64_shoff # define ehdr_shentsize ehdr64_shentsize # define ehdr_shstrndx ehdr64_shstrndx @@ -63,6 +62,7 @@ # define sym_name sym64_name # define sym_value sym64_value # define sym_shndx sym64_shndx +# define long_size 8 #else # define extable_ent_size 8 # define compare_extable compare_extable_32 @@ -70,7 +70,6 @@ # define sort_mcount_loc sort_mcount_loc_32 # define elf_mcount_loc elf_mcount_loc_32 # define do_sort do_sort_32 -# define uint_t uint32_t # define ehdr_shoff ehdr32_shoff # define ehdr_shentsize ehdr32_shentsize # define ehdr_shstrndx ehdr32_shstrndx @@ -86,6 +85,7 @@ # define sym_name sym32_name # define sym_value sym32_value # define sym_shndx sym32_shndx +# define long_size 4 #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) @@ -193,25 +193,25 @@ 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; + uint64_t start_mcount_loc; + uint64_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 - shdr_addr(emloc->init_data_sec) + uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + shdr_offset(emloc->init_data_sec); - uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; + uint64_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); + qsort(start_loc, count/long_size, long_size, 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) +static void get_mcount_loc(uint64_t *_start, uint64_t *_stop) { FILE *file_start, *file_stop; char start_buff[20]; @@ -277,8 +277,8 @@ static int do_sort(Elf_Ehdr *ehdr, 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; + uint64_t _start_mcount_loc = 0; + uint64_t _stop_mcount_loc = 0; #endif #if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) unsigned int orc_ip_size = 0; -- cgit v1.2.3 From 58d87678a0f46c6120904b4326aaf5ebf4454c69 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Tue, 7 Jan 2025 22:32:17 -0500 Subject: scripts/sorttable: Move code from sorttable.h into sorttable.c Instead of having the main code live in a header file and included twice with MACROs that define the Elf structures for 64 bit or 32 bit, move the code in the C file now that the Elf structures are defined in a union that has both. All accesses to the Elf structure fields are done through helper function pointers. If the file being parsed if for a 64 bit architecture, all the helper functions point to the 64 bit versions to retrieve the Elf fields. The same is true if the architecture is 32 bit, where the function pointers will point to the 32 bit helper functions. Note, when the value of a field can be either 32 bit or 64 bit, a 64 bit is always returned, as it works for the 32 bit code as well. This makes the code easier to read and maintain, and it now all exists in sorttable.c and sorttable.h may be removed. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: https://lore.kernel.org/20250107223217.6f7f96a5@gandalf.local.home Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 473 ++++++++++++++++++++++++++++++++++++++++++++++++-- scripts/sorttable.h | 485 ---------------------------------------------------- 2 files changed, 460 insertions(+), 498 deletions(-) delete mode 100644 scripts/sorttable.h (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 20615de18276..ff9b60fc0dd8 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -327,10 +327,423 @@ static inline void *get_index(void *start, int entsize, int index) return start + (entsize * index); } -/* 32 bit and 64 bit are very similar */ -#include "sorttable.h" -#define SORTTABLE_64 -#include "sorttable.h" + +static int (*compare_extable)(const void *a, const void *b); +static uint64_t (*ehdr_shoff)(Elf_Ehdr *ehdr); +static uint16_t (*ehdr_shstrndx)(Elf_Ehdr *ehdr); +static uint16_t (*ehdr_shentsize)(Elf_Ehdr *ehdr); +static uint16_t (*ehdr_shnum)(Elf_Ehdr *ehdr); +static uint64_t (*shdr_addr)(Elf_Shdr *shdr); +static uint64_t (*shdr_offset)(Elf_Shdr *shdr); +static uint64_t (*shdr_size)(Elf_Shdr *shdr); +static uint64_t (*shdr_entsize)(Elf_Shdr *shdr); +static uint32_t (*shdr_link)(Elf_Shdr *shdr); +static uint32_t (*shdr_name)(Elf_Shdr *shdr); +static uint32_t (*shdr_type)(Elf_Shdr *shdr); +static uint8_t (*sym_type)(Elf_Sym *sym); +static uint32_t (*sym_name)(Elf_Sym *sym); +static uint64_t (*sym_value)(Elf_Sym *sym); +static uint16_t (*sym_shndx)(Elf_Sym *sym); + +static int extable_ent_size; +static int long_size; + + +#ifdef UNWINDER_ORC_ENABLED +/* ORC unwinder only support X86_64 */ +#include <asm/orc_types.h> + +#define ERRSTR_MAXSZ 256 + +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 pthread_t mcount_sort_thread; + +struct elf_mcount_loc { + Elf_Ehdr *ehdr; + Elf_Shdr *init_data_sec; + uint64_t start_mcount_loc; + uint64_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; + uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + + shdr_offset(emloc->init_data_sec); + uint64_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; + unsigned char *start_loc = (void *)emloc->ehdr + offset; + + qsort(start_loc, count/long_size, long_size, compare_extable); + return NULL; +} + +/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ +static void get_mcount_loc(uint64_t *_start, uint64_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 *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}; + uint64_t _start_mcount_loc = 0; + uint64_t _stop_mcount_loc = 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")) { + get_mcount_loc(&_start_mcount_loc, &_stop_mcount_loc); + mstruct.ehdr = ehdr; + mstruct.init_data_sec = shdr; + mstruct.start_mcount_loc = _start_mcount_loc; + mstruct.stop_mcount_loc = _stop_mcount_loc; + } +#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 + +#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 + shdr_offset(extab_sec); + strtab = (const char *)ehdr + shdr_offset(strtab_sec); + symtab = (const Elf_Sym *)((const char *)ehdr + shdr_offset(symtab_sec)); + + 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) { @@ -399,7 +812,6 @@ 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; Elf_Ehdr *ehdr = addr; table_sort_t custom_sort = NULL; @@ -462,29 +874,64 @@ static int do_file(char const *const fname, void *addr) 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); + + 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; + long_size = 4; + extable_ent_size = 8; break; case ELFCLASS64: - { 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; - } - rc = do_sort_64(ehdr, fname, custom_sort); + return -1; } + + 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; + long_size = 8; + extable_ent_size = 16; + break; default: fprintf(stderr, "unrecognized ELF class %d %s\n", ehdr->e32.e_ident[EI_CLASS], fname); - break; + return -1; } - return rc; + return do_sort(ehdr, fname, custom_sort); } int main(int argc, char *argv[]) diff --git a/scripts/sorttable.h b/scripts/sorttable.h deleted file mode 100644 index 17a8541a10d6..000000000000 --- a/scripts/sorttable.h +++ /dev/null @@ -1,485 +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 ehdr_shoff -#undef ehdr_shentsize -#undef ehdr_shstrndx -#undef ehdr_shnum -#undef shdr_addr -#undef shdr_offset -#undef shdr_link -#undef shdr_size -#undef shdr_name -#undef shdr_type -#undef shdr_entsize -#undef sym_type -#undef sym_name -#undef sym_value -#undef sym_shndx -#undef long_size - -#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 ehdr_shoff ehdr64_shoff -# define ehdr_shentsize ehdr64_shentsize -# define ehdr_shstrndx ehdr64_shstrndx -# define ehdr_shnum ehdr64_shnum -# define shdr_addr shdr64_addr -# define shdr_offset shdr64_offset -# define shdr_link shdr64_link -# define shdr_size shdr64_size -# define shdr_name shdr64_name -# define shdr_type shdr64_type -# define shdr_entsize shdr64_entsize -# define sym_type sym64_type -# define sym_name sym64_name -# define sym_value sym64_value -# define sym_shndx sym64_shndx -# define long_size 8 -#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 ehdr_shoff ehdr32_shoff -# define ehdr_shentsize ehdr32_shentsize -# define ehdr_shstrndx ehdr32_shstrndx -# define ehdr_shnum ehdr32_shnum -# define shdr_addr shdr32_addr -# define shdr_offset shdr32_offset -# define shdr_link shdr32_link -# define shdr_size shdr32_size -# define shdr_name shdr32_name -# define shdr_type shdr32_type -# define shdr_entsize shdr32_entsize -# define sym_type sym32_type -# define sym_name sym32_name -# define sym_value sym32_value -# define sym_shndx sym32_shndx -# define long_size 4 -#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 - -#ifdef MCOUNT_SORT_ENABLED -pthread_t mcount_sort_thread; - -struct elf_mcount_loc { - Elf_Ehdr *ehdr; - Elf_Shdr *init_data_sec; - uint64_t start_mcount_loc; - uint64_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; - uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) - + shdr_offset(emloc->init_data_sec); - uint64_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; - unsigned char *start_loc = (void *)emloc->ehdr + offset; - - qsort(start_loc, count/long_size, long_size, compare_extable); - return NULL; -} - -/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ -static void get_mcount_loc(uint64_t *_start, uint64_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 *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}; - uint64_t _start_mcount_loc = 0; - uint64_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 - - 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")) { - get_mcount_loc(&_start_mcount_loc, &_stop_mcount_loc); - mstruct.ehdr = ehdr; - mstruct.init_data_sec = shdr; - 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 = 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 */ - -#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 + shdr_offset(extab_sec); - strtab = (const char *)ehdr + shdr_offset(strtab_sec); - symtab = (const Elf_Sym *)((const char *)ehdr + shdr_offset(symtab_sec)); - - 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: -#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; -} -- cgit v1.2.3 From 4acda8edefa1ce66d3de845f1c12745721cd14c3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Sun, 5 Jan 2025 11:22:25 -0500 Subject: scripts/sorttable: Get start/stop_mcount_loc from ELF file directly The get_mcount_loc() does a cheesy trick to find the start_mcount_loc and stop_mcount_loc values. That trick is: file_start = popen(" grep start_mcount System.map | awk '{print $1}' ", "r"); and file_stop = popen(" grep stop_mcount System.map | awk '{print $1}' ", "r"); Those values are stored in the Elf symbol table. Use that to capture those values. Using the symbol table is more efficient and more robust. The above could fail if another variable had "start_mcount" or "stop_mcount" as part of its name. Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Link: https://lore.kernel.org/20250105162346.817157047@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 95 +++++++++++++++++++++++++---------------------------- 1 file changed, 45 insertions(+), 50 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index ff9b60fc0dd8..656c1e9b5ad9 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -472,42 +472,41 @@ static void *sort_mcount_loc(void *arg) } /* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ -static void get_mcount_loc(uint64_t *_start, uint64_t *_stop) +static void get_mcount_loc(struct elf_mcount_loc *emloc, Elf_Shdr *symtab_sec, + const char *strtab) { - FILE *file_start, *file_stop; - char start_buff[20]; - char stop_buff[20]; - int len = 0; + 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; + } - file_start = popen(" grep start_mcount System.map | awk '{print $1}' ", "r"); - if (!file_start) { + if (!emloc->start_mcount_loc) { fprintf(stderr, "get start_mcount_loc error!"); return; } - file_stop = popen(" grep stop_mcount System.map | awk '{print $1}' ", "r"); - if (!file_stop) { + if (!emloc->stop_mcount_loc) { 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) @@ -538,8 +537,6 @@ static int do_sort(Elf_Ehdr *ehdr, unsigned int shstrndx; #ifdef MCOUNT_SORT_ENABLED struct elf_mcount_loc mstruct = {0}; - uint64_t _start_mcount_loc = 0; - uint64_t _stop_mcount_loc = 0; #endif #ifdef UNWINDER_ORC_ENABLED unsigned int orc_ip_size = 0; @@ -577,13 +574,8 @@ static int do_sort(Elf_Ehdr *ehdr, #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; + if (!strcmp(secstrings + idx, ".init.data")) mstruct.init_data_sec = shdr; - mstruct.start_mcount_loc = _start_mcount_loc; - mstruct.stop_mcount_loc = _stop_mcount_loc; - } #endif #ifdef UNWINDER_ORC_ENABLED @@ -627,23 +619,6 @@ static int do_sort(Elf_Ehdr *ehdr, 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; @@ -663,6 +638,26 @@ static int do_sort(Elf_Ehdr *ehdr, 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 { -- cgit v1.2.3 From def35da76073fcf43c2fae4942ebe55b60dc84a6 Mon Sep 17 00:00:00 2001 From: Costa Shulyupin <costa.shul@redhat.com> Date: Mon, 9 Dec 2024 10:29:57 +0200 Subject: scripts/tags.sh: Tag timer definitions For timer definitions like DEFINE_TIMER(mytimer, mytimer_handler); ctags generates tags `DEFINE_TIMER` and skips `mytimer` because it doesn't expand the DEFINE_TIMER macro. Configure ctags to generate tag for `mytimer` ans skip the `DEFINE_TIMER` tag in such cases. Signed-off-by: Costa Shulyupin <costa.shul@redhat.com> Link: https://lore.kernel.org/r/20241209083004.911013-2-costa.shul@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> --- scripts/tags.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/tags.sh b/scripts/tags.sh index b21236377998..7102f14fc775 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -188,6 +188,7 @@ 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/' @@ -260,7 +261,7 @@ exuberant() # identifiers to ignore by ctags local ign=( ACPI_EXPORT_SYMBOL - DEFINE_{TRACE,MUTEX} + DEFINE_{TRACE,MUTEX,TIMER} EXPORT_SYMBOL EXPORT_SYMBOL_GPL EXPORT_TRACEPOINT_SYMBOL EXPORT_TRACEPOINT_SYMBOL_GPL ____cacheline_aligned ____cacheline_aligned_in_smp -- cgit v1.2.3 From 634d34e856ca0123f96613ffaf1852a1d3b46880 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx@linutronix.de> Date: Fri, 29 Nov 2024 11:37:45 +0100 Subject: scripts/spdxcheck: Parse j2 comments correctly j2 files use '#}' as comment closure, which trips up the SPDX parser: tools/.../definition.j2: 1:36 Invalid token: #} Handle those comments correctly by removing the closure. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/878qt2xr46.ffs@tglx Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> --- scripts/spdxcheck.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'scripts') diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 8b8fb115fc81..fe57c9aecf37 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -217,6 +217,9 @@ class id_parser(object): # 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 # -- cgit v1.2.3 From 154916f4b59dc2228caad5fc98e9e6a7e1a84e19 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn <lukas.bulwahn@redhat.com> Date: Wed, 8 Jan 2025 13:52:07 +0100 Subject: scripts/spdxcheck: Handle license identifiers in Jinja comments Commit 4b132aacb076 ("tools: Add xdrgen") adds a tool, which uses Jinja template files, i.e., files with the j2 file extension, for its lightweight code generation. These template files for this tool have proper headers with the SPDX License information, which are included as Jinja comments by enclosing the text with '{#' and '#}'. Sofar, the spdxcheck script does not support to properly parse this license information in Jinja comments and it reports back with 'Invalid token: #}'. Parse Jinja comments properly by stripping the known Jinja comment suffix. Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com> Link: https://lore.kernel.org/r/20250108125207.57486-1-lukas.bulwahn@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> --- scripts/spdxcheck.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'scripts') diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index fe57c9aecf37..8d608f61bf37 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -214,6 +214,9 @@ 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() -- cgit v1.2.3 From c23d1f7e15d11d6ae6c70824e04ba9ed0299de0a Mon Sep 17 00:00:00 2001 From: Miguel Ojeda <ojeda@kernel.org> Date: Mon, 9 Dec 2024 22:25:44 +0100 Subject: rust: document `bindgen` 0.71.0 regression `bindgen` 0.71.0 regressed [1] on the "`--version` requires header" issue which appeared in 0.69.0 first [2] and was fixed in 0.69.1. It has been fixed again in 0.71.1 [3]. Thus document it so that, when we upgrade the minimum past 0.69.0 in the future, we do not forget that we cannot remove the workaround until we arrive at 0.71.1 at least. Link: https://github.com/rust-lang/rust-bindgen/issues/3039 [1] Link: https://github.com/rust-lang/rust-bindgen/issues/2677 [2] Link: https://github.com/rust-lang/rust-bindgen/blob/main/CHANGELOG.md#v0711-2024-12-09 [3] Reviewed-by: Fiona Behrens <me@kloenk.dev> Reviewed-by: Alice Ryhl <aliceryhl@google.com> Link: https://lore.kernel.org/r/20241209212544.1977065-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda <ojeda@kernel.org> --- init/Kconfig | 6 ++++-- scripts/rust_is_available.sh | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/init/Kconfig b/init/Kconfig index a20e6efd3f0f..e8d2b5128f87 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1989,8 +1989,10 @@ config BINDGEN_VERSION_TEXT string depends on RUST # 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). default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)" # 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=$? -- cgit v1.2.3 From 0730422bced5e8325fb6806d9a80bb10673588e6 Mon Sep 17 00:00:00 2001 From: Tamir Duberstein <tamird@gmail.com> Date: Mon, 16 Dec 2024 10:54:22 -0500 Subject: rust: use host dylib naming convention to support macOS Because the `macros` crate exposes procedural macros, it must be compiled as a dynamic library (so it can be loaded by the compiler at compile-time). Before this change the resulting artifact was always named `libmacros.so`, which works on hosts where this matches the naming convention for dynamic libraries. However the proper name on macOS would be `libmacros.dylib`. This turns out to matter even when the dependency is passed with a path (`--extern macros=path/to/libmacros.so` rather than `--extern macros`) because rustc uses the file name to infer the type of the library (see link). This is because there's no way to specify both the path to and the type of the external library via CLI flags. The compiler could speculatively parse the file to determine its type, but it does not do so today. This means that libraries that match neither rustc's naming convention for static libraries nor the platform's naming convention for dynamic libraries are *rejected*. The only solution I've found is to follow the host platform's naming convention. This patch does that by querying the compiler to determine the appropriate name for the artifact. This allows the kernel to build with CONFIG_RUST=y on macOS. Link: https://github.com/rust-lang/rust/blob/d829780/compiler/rustc_metadata/src/locator.rs#L728-L752 Tested-by: Daniel Gomez <da.gomez@samsung.com> Co-developed-by: Fiona Behrens <me@kloenk.dev> Signed-off-by: Fiona Behrens <me@kloenk.dev> Signed-off-by: Tamir Duberstein <tamird@gmail.com> Tested-by: Andreas Hindborg <a.hindborg@kernel.org> Link: https://lore.kernel.org/r/20241216-b4-dylib-host-macos-v7-1-cfc507681447@gmail.com [ Added `MAKEFLAGS=`s to avoid jobserver warnings. Removed space. Reworded title. - Miguel ] Signed-off-by: Miguel Ojeda <ojeda@kernel.org> --- .gitignore | 1 + Makefile | 2 +- rust/Makefile | 22 ++++++++++++---------- scripts/generate_rust_analyzer.py | 15 +++++++++++---- 4 files changed, 25 insertions(+), 15 deletions(-) (limited to 'scripts') diff --git a/.gitignore b/.gitignore index 6839cf84acda..5937c74d3dc1 100644 --- a/.gitignore +++ b/.gitignore @@ -22,6 +22,7 @@ *.dtb.S *.dtbo.S *.dwo +*.dylib *.elf *.gcno *.gcda diff --git a/Makefile b/Makefile index e5b8a8832c0c..80d9943d9744 100644 --- a/Makefile +++ b/Makefile @@ -1571,7 +1571,7 @@ MRPROPER_FILES += include/config include/generated \ certs/x509.genkey \ vmlinux-gdb.py \ rpmbuild \ - rust/libmacros.so + rust/libmacros.so rust/libmacros.dylib # clean - Delete most, but leave enough to build external modules # diff --git a/rust/Makefile b/rust/Makefile index 161e7cf67c97..5c8f35f5ada2 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -11,9 +11,6 @@ always-$(CONFIG_RUST) += exports_core_generated.h obj-$(CONFIG_RUST) += helpers/helpers.o CFLAGS_REMOVE_helpers/helpers.o = -Wmissing-prototypes -Wmissing-declarations -always-$(CONFIG_RUST) += libmacros.so -no-clean-files += libmacros.so - always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs obj-$(CONFIG_RUST) += bindings.o kernel.o always-$(CONFIG_RUST) += exports_helpers_generated.h \ @@ -38,9 +35,14 @@ obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o always-$(subst y,$(CONFIG_RUST),$(CONFIG_JUMP_LABEL)) += kernel/generated_arch_static_branch_asm.rs -# Avoids running `$(RUSTC)` for the sysroot when it may not be available. +# Avoids running `$(RUSTC)` when it may not be available. ifdef CONFIG_RUST +libmacros_name := $(shell MAKEFLAGS= $(RUSTC) --print file-names --crate-name macros --crate-type proc-macro - </dev/null) +libmacros_extension := $(patsubst libmacros.%,%,$(libmacros_name)) + +always-$(CONFIG_RUST) += $(libmacros_name) + # `$(rust_flags)` is passed in case the user added `--sysroot`. rustc_sysroot := $(shell MAKEFLAGS= $(RUSTC) $(rust_flags) --print sysroot) rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2) @@ -109,10 +111,10 @@ rustdoc-ffi: $(src)/ffi.rs rustdoc-core FORCE +$(call if_changed,rustdoc) rustdoc-kernel: private rustc_target_flags = --extern ffi \ - --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \ + --extern build_error --extern macros \ --extern bindings --extern uapi rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-ffi rustdoc-macros \ - rustdoc-compiler_builtins $(obj)/libmacros.so \ + rustdoc-compiler_builtins $(obj)/$(libmacros_name) \ $(obj)/bindings.o FORCE +$(call if_changed,rustdoc) @@ -362,10 +364,10 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@ -Clink-args='$(call escsq,$(KBUILD_HOSTLDFLAGS))' \ --emit=dep-info=$(depfile) --emit=link=$@ --extern proc_macro \ --crate-type proc-macro \ - --crate-name $(patsubst lib%.so,%,$(notdir $@)) $< + --crate-name $(patsubst lib%.$(libmacros_extension),%,$(notdir $@)) $< # Procedural macros can only be used with the `rustc` that compiled it. -$(obj)/libmacros.so: $(src)/macros/lib.rs FORCE +$(obj)/$(libmacros_name): $(src)/macros/lib.rs FORCE +$(call if_changed_dep,rustc_procmacro) quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@ @@ -382,7 +384,7 @@ quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $(cmd_objtool) rust-analyzer: - $(Q)$(srctree)/scripts/generate_rust_analyzer.py \ + $(Q)MAKEFLAGS= $(srctree)/scripts/generate_rust_analyzer.py \ --cfgs='core=$(core-cfgs)' \ $(realpath $(srctree)) $(realpath $(objtree)) \ $(rustc_sysroot) $(RUST_LIB_SRC) $(if $(KBUILD_EXTMOD),$(srcroot)) \ @@ -443,7 +445,7 @@ $(obj)/uapi.o: $(src)/uapi/lib.rs \ $(obj)/kernel.o: private rustc_target_flags = --extern ffi \ --extern build_error --extern macros --extern bindings --extern uapi $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/build_error.o \ - $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE + $(obj)/$(libmacros_name) $(obj)/bindings.o $(obj)/uapi.o FORCE +$(call if_changed_rule,rustc_library) ifdef CONFIG_JUMP_LABEL diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index 09e1d166d8d2..aa8ea1a4dbe5 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): @@ -35,8 +36,7 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): 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({ + crate = { "display_name": display_name, "root_module": str(root_module), "is_workspace_member": is_workspace_member, @@ -47,7 +47,15 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): "env": { "RUST_MODFILE": "This is only for rust-analyzer" } - }) + } + 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) # First, the ones in `rust/` since they are a bit special. append_crate( @@ -70,7 +78,6 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): [], is_proc_macro=True, ) - crates[-1]["proc_macro_dylib_path"] = f"{objtree}/rust/libmacros.so" append_crate( "build_error", -- cgit v1.2.3 From 1e5f6771c247b28135307058d2cfe3b0153733dc Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt@goodmis.org> Date: Fri, 10 Jan 2025 07:54:59 -0500 Subject: scripts/sorttable: Use a structure of function pointers for elf helpers Instead of having a series of function pointers that gets assigned to the Elf64 or Elf32 versions, put them all into a single structure and use that. Add the helper function that chooses the structure into the macros that build the different versions of the elf functions. Link: https://lore.kernel.org/all/CAHk-=wiafEyX7UgOeZgvd6fvuByE5WXUPh9599kwOc_d-pdeug@mail.gmail.com/ Cc: bpf <bpf@vger.kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Zheng Yejian <zhengyejian1@huawei.com> Cc: Martin Kelly <martin.kelly@crowdstrike.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: https://lore.kernel.org/20250110075459.13d4b94c@gandalf.local.home Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org> --- scripts/sorttable.c | 175 +++++++++++++++++++++++++++++++++++----------------- 1 file changed, 118 insertions(+), 57 deletions(-) (limited to 'scripts') diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 656c1e9b5ad9..9f41575afd7a 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -85,6 +85,25 @@ static uint64_t (*r8)(const uint64_t *); static void (*w)(uint32_t, uint32_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); +} e; + static uint64_t ehdr64_shoff(Elf_Ehdr *ehdr) { return r8(&ehdr->e64.e_shoff); @@ -95,6 +114,11 @@ 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) \ { \ @@ -104,6 +128,11 @@ static uint16_t ehdr64_##fn_name(Elf_Ehdr *ehdr) \ 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) @@ -119,6 +148,11 @@ static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ 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) \ @@ -130,6 +164,11 @@ static uint64_t shdr64_##fn_name(Elf_Shdr *shdr) \ 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) \ @@ -141,6 +180,10 @@ static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ 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) @@ -161,6 +204,11 @@ static uint64_t sym64_##fn_name(Elf_Sym *sym) \ 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) \ @@ -172,6 +220,11 @@ static uint32_t sym64_##fn_name(Elf_Sym *sym) \ 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) \ @@ -183,6 +236,11 @@ static uint16_t sym64_##fn_name(Elf_Sym *sym) \ 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) @@ -195,6 +253,11 @@ 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) @@ -322,29 +385,16 @@ static int compare_extable_64(const void *a, const void *b) 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 (*compare_extable)(const void *a, const void *b); -static uint64_t (*ehdr_shoff)(Elf_Ehdr *ehdr); -static uint16_t (*ehdr_shstrndx)(Elf_Ehdr *ehdr); -static uint16_t (*ehdr_shentsize)(Elf_Ehdr *ehdr); -static uint16_t (*ehdr_shnum)(Elf_Ehdr *ehdr); -static uint64_t (*shdr_addr)(Elf_Shdr *shdr); -static uint64_t (*shdr_offset)(Elf_Shdr *shdr); -static uint64_t (*shdr_size)(Elf_Shdr *shdr); -static uint64_t (*shdr_entsize)(Elf_Shdr *shdr); -static uint32_t (*shdr_link)(Elf_Shdr *shdr); -static uint32_t (*shdr_name)(Elf_Shdr *shdr); -static uint32_t (*shdr_type)(Elf_Shdr *shdr); -static uint8_t (*sym_type)(Elf_Sym *sym); -static uint32_t (*sym_name)(Elf_Sym *sym); -static uint64_t (*sym_value)(Elf_Sym *sym); -static uint16_t (*sym_shndx)(Elf_Sym *sym); - static int extable_ent_size; static int long_size; @@ -864,7 +914,30 @@ static int do_file(char const *const fname, void *addr) } switch (ehdr->e32.e_ident[EI_CLASS]) { - case ELFCLASS32: + 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, + }; + + 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, @@ -872,26 +945,32 @@ static int do_file(char const *const fname, void *addr) return -1; } - 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; - long_size = 4; - extable_ent_size = 8; + } break; - case ELFCLASS64: + 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, + }; + + 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, @@ -900,25 +979,7 @@ static int do_file(char const *const fname, void *addr) return -1; } - 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; - long_size = 8; - extable_ent_size = 16; - + } break; default: fprintf(stderr, "unrecognized ELF class %d %s\n", -- cgit v1.2.3 From d9ecb92b4fbbbb0a9993017da8d044541ca35886 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 3 Dec 2024 22:59:58 +0900 Subject: kbuild: deb-pkg: do not include empty hook directories The linux-image package currently includes empty hook directories (/etc/kernel/{pre,post}{inst,rm}.d/ by default). These directories were perhaps intended as a fail-safe in case no hook scripts exist there. However, they are really unnecessary because the run-parts command is already guarded by the following check: test -d ${debhookdir}/${script}.d && run-parts ... The only difference is that the run-parts command either runs for empty directories (resulting in a no-op) or is skipped entirely. The maintainer scripts will succeed without these dummy directories. The linux-image packages from the Debian kernel do not contain /etc/kernel/*.d/, either. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/package/builddeb | 2 -- 1 file changed, 2 deletions(-) (limited to 'scripts') diff --git a/scripts/package/builddeb b/scripts/package/builddeb index ad7aba0f268e..85fe8f56bb9b 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -76,8 +76,6 @@ install_maint_scripts () { # so do we; recent versions of dracut and initramfs-tools will obey this. debhookdir=${KDEB_HOOKDIR:-/etc/kernel} for script in postinst postrm preinst prerm; do - mkdir -p "${pdir}${debhookdir}/${script}.d" - mkdir -p "${pdir}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" #!/bin/sh -- cgit v1.2.3 From ac2c30f98f28a6606af89ce44bff77af5d558fe8 Mon Sep 17 00:00:00 2001 From: Johannes Schauer Marin Rodrigues <josch@mister-muffin.de> Date: Tue, 3 Dec 2024 17:17:35 +0100 Subject: kbuild: deb-pkg: allow hooks also in /usr/share/kernel By passing an additional directory to run-parts, allow Debian and its derivatives to ship maintainer scripts in /usr while at the same time allowing the local admin to override or disable them by placing hooks of the same name in /etc. This adds support for the mechanism described in the UAPI Configuration Files Specification for kernel hooks. The same idea is also used by udev, systemd or modprobe for their config files. https://uapi-group.org/specifications/specs/configuration_files_specification/ This functionality relies on run-parts 5.21 or later. It is the responsibility of packages installing hooks into /usr/share/kernel to also declare a Depends: debianutils (>= 5.21). KDEB_HOOKDIR can be used to change the list of directories that is searched. By default, /etc/kernel and /usr/share/kernel are hook directories. Since the list of directories in KDEB_HOOKDIR is separated by spaces, the paths must not contain the space character themselves. Signed-off-by: Johannes Schauer Marin Rodrigues <josch@mister-muffin.de> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/package/builddeb | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'scripts') diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 85fe8f56bb9b..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 @@ -74,7 +76,7 @@ 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}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" @@ -88,7 +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}" -- cgit v1.2.3 From 5f73e7d0386d970a7d0e9de5a58d53114de85033 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 10 Dec 2024 19:06:17 +0900 Subject: kbuild: refactor cross-compiling linux-headers package Since commit 13b25489b6f8 ("kbuild: change working directory to external module directory with M="), when cross-building host programs for the linux-headers package, the "Entering directory" and "Leaving directory" messages appear multiple times, and each object path shown is relative to the working directory. This makes it difficult to track which objects are being rebuilt. In hindsight, using the external module build (M=) was not a good idea. This commit simplifies the script by leveraging the run-command target, resulting in a cleaner build log again. [Before] $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- bindeb-pkg [ snip ] Rebuilding host programs with aarch64-linux-gnu-gcc... make[5]: Entering directory '/home/masahiro/linux' make[6]: Entering directory '/home/masahiro/linux/debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+' HOSTCC scripts/kallsyms HOSTCC scripts/sorttable HOSTCC scripts/asn1_compiler make[6]: Leaving directory '/home/masahiro/linux/debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+' make[5]: Leaving directory '/home/masahiro/linux' make[5]: Entering directory '/home/masahiro/linux' make[6]: Entering directory '/home/masahiro/linux/debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+' HOSTCC scripts/basic/fixdep HOSTCC scripts/mod/modpost.o HOSTCC scripts/mod/file2alias.o HOSTCC scripts/mod/sumversion.o HOSTCC scripts/mod/symsearch.o HOSTLD scripts/mod/modpost make[6]: Leaving directory '/home/masahiro/linux/debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+' make[5]: Leaving directory '/home/masahiro/linux' [After] $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- bindeb-pkg [ snip ] HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/basic/fixdep HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/kallsyms HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/sorttable HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/asn1_compiler HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/mod/modpost.o HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/mod/file2alias.o HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/mod/sumversion.o HOSTCC debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/mod/symsearch.o HOSTLD debian/linux-headers-6.13.0-rc1+/usr/src/linux-headers-6.13.0-rc1+/scripts/mod/modpost Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/package/install-extmod-build | 33 +++++++++------------------------ 1 file changed, 9 insertions(+), 24 deletions(-) (limited to 'scripts') diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index d3c5b104c063..bb6e23c1174e 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), $(CC), and $(build) will be expanded by Make + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC=$(CC) VPATH= srcroot=. $(build)='"${destdir}"/scripts - rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild" + rm -f "${destdir}/scripts/Kbuild" fi find "${destdir}" \( -name '.*.cmd' -o -name '*.o' \) -delete -- cgit v1.2.3 From 1f937a4bcb0472015818f30f4d3c5546d3f09933 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 10 Dec 2024 19:24:41 +0900 Subject: kbuild: suppress stdout from merge_config for silent builds merge_config does not respect the Make's -s (--silent) option. Let's sink the stdout from merge_config for silent builds. This commit does not cater to the direct invocation of merge_config.sh (e.g. arch/mips/Makefile). Reported-by: Leon Romanovsky <leon@kernel.org> Closes: https://lore.kernel.org/all/e534ce33b0e1060eb85ece8429810f087b034c88.1733234008.git.leonro@nvidia.com/ Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Tested-by: Leon Romanovsky <leon@kernel.org> Reviewed-by: Nathan Chancellor <nathan@kernel.org> --- scripts/Makefile.defconf | 13 +++++++------ scripts/kconfig/Makefile | 4 +++- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'scripts') 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/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 -- cgit v1.2.3 From 82a1978d0fdc28e561bc4d98ea155dd322f33c19 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Wed, 18 Dec 2024 19:37:08 +0900 Subject: kheaders: use 'tar' instead of 'cpio' for copying files The 'cpio' command is used solely for copying header files to the temporary directory. However, there is no strong reason to use 'cpio' for this purpose. For example, scripts/package/install-extmod-build uses the 'tar' command to copy files. This commit replaces the use of 'cpio' with 'tar' because 'tar' is already used in this script to generate kheaders_data.tar.xz anyway. Performance-wide, there is no significant difference between 'cpio' and 'tar'. [Before] $ rm -fr kheaders; mkdir kheaders $ time sh -c ' for f in include arch/x86/include do find "$f" -name "*.h" done | cpio --quiet -pd kheaders ' real 0m0.148s user 0m0.021s sys 0m0.140s [After] $ rm -fr kheaders; mkdir kheaders $ time sh -c ' for f in include arch/x86/include do find "$f" -name "*.h" done | tar -c -f - -T - | tar -xf - -C kheaders ' real 0m0.098s user 0m0.024s sys 0m0.131s Revert commit 69ef0920bdd3 ("Docs: Add cpio requirement to changes.rst") because 'cpio' is not used anywhere else during the kernel build. Please note that the built-in initramfs is created by the in-tree tool, usr/gen_init_cpio, so it does not rely on the external 'cpio' command at all. Remove 'cpio' from the package build dependencies as well. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- Documentation/process/changes.rst | 6 ------ kernel/gen_kheaders.sh | 13 ++----------- scripts/package/PKGBUILD | 1 - scripts/package/mkdebian | 2 +- 4 files changed, 3 insertions(+), 19 deletions(-) (limited to 'scripts') diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 82b5e378eebf..a0beca805362 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -59,7 +59,6 @@ iptables 1.4.2 iptables -V openssl & libcrypto 1.0.0 openssl version bc 1.06.95 bc --version Sphinx\ [#f1]_ 2.4.4 sphinx-build --version -cpio any cpio --version GNU tar 1.28 tar --version gtags (optional) 6.6.5 gtags --version mkimage (optional) 2017.01 mkimage --version @@ -536,11 +535,6 @@ mcelog - <https://www.mcelog.org/> -cpio ----- - -- <https://www.gnu.org/software/cpio/> - Networking ********** diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index ddfd1177567f..55f493d83b8f 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -14,13 +14,6 @@ include/ arch/$SRCARCH/include/ " -if ! command -v cpio >/dev/null; then - echo >&2 "***" - echo >&2 "*** 'cpio' could not be found." - echo >&2 "***" - exit 1 -fi - # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. @@ -73,15 +66,13 @@ if [ "$building_out_of_srctree" ]; then cd $srctree for f in $dir_list do find "$f" -name "*.h"; - done | cpio --quiet -pd "${tmpdir}" + done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" ) fi -# The second CPIO can complain if files already exist which can happen with out -# of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; -done | cpio --quiet -pdu "${tmpdir}" >/dev/null 2>&1 +done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" # Always exclude include/generated/utsversion.h # Otherwise, the contents of the tarball may vary depending on the build steps. diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index dca706617adc..0cf3a55b05e1 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 diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index b038a1380b8a..b6dd98ca860b 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -205,7 +205,7 @@ 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.${sourcename}.nokernelheaders>, kmod, libelf-dev:native, libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, -- cgit v1.2.3 From ad2091dee019a68145610081a75fae3b90f0c44d Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer <eb@emlix.com> Date: Thu, 19 Dec 2024 08:20:34 +0100 Subject: kconfig: qconf: use preferred form of QString API A QString constructed from a character literal of length 0, i.e. "", is not "null" for historical reasons. This does not matter here so use the preferred method isEmpty() instead. Also directly construct empty QString objects instead of passing in an empty character literal that has to be parsed into an empty object first. Signed-off-by: Rolf Eike Beer <eb@emlix.com> Link: https://doc.qt.io/qt-6/qstring.html#distinction-between-null-and-empty-strings Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/kconfig/qconf.cc | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'scripts') 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())) { -- cgit v1.2.3 From 5963913bb57f15f198361bc7f1389c756b98f25f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Sun, 29 Dec 2024 00:45:29 +0900 Subject: modpost: zero-pad CRC values in modversion_info array I do not think the '#' flag is useful here because adding the explicit '0x' is clearer. Add the '0' flag to zero-pad the CRC values. This change gives better alignment in the generated *.mod.c files. There is no impact to the compiled modules. [Before] $ grep -A5 modversion_info fs/efivarfs/efivarfs.mod.c static const struct modversion_info ____versions[] __used __section("__versions") = { { 0x907d14d, "blocking_notifier_chain_register" }, { 0x53d3b64, "simple_inode_init_ts" }, { 0x65487097, "__x86_indirect_thunk_rax" }, { 0x122c3a7e, "_printk" }, [After] $ grep -A5 modversion_info fs/efivarfs/efivarfs.mod.c static const struct modversion_info ____versions[] __used __section("__versions") = { { 0x0907d14d, "blocking_notifier_chain_register" }, { 0x053d3b64, "simple_inode_init_ts" }, { 0x65487097, "__x86_indirect_thunk_rax" }, { 0x122c3a7e, "_printk" }, Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/mod/modpost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7ea59dc4926b..dc907014108b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1832,7 +1832,7 @@ static void add_versions(struct buffer *b, struct module *mod) s->name, mod->name); break; } - buf_printf(b, "\t{ %#8x, \"%s\" },\n", + buf_printf(b, "\t{ 0x%08x, \"%s\" },\n", s->crc, s->name); } -- cgit v1.2.3 From 45c9c4101d3d2fdfa00852274bbebba65fcc3cf2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:38 +0900 Subject: genksyms: fix memory leak when the same symbol is added from source When a symbol that is already registered is added again, __add_symbol() returns without freeing the symbol definition, making it unreachable. The following test cases demonstrate different memory leak points. [Test Case 1] Forward declaration with exactly the same definition $ cat foo.c #include <linux/export.h> void foo(void); void foo(void) {} EXPORT_SYMBOL(foo); [Test Case 2] Forward declaration with a different definition (e.g. attribute) $ cat foo.c #include <linux/export.h> void foo(void); __attribute__((__section__(".ref.text"))) void foo(void) {} EXPORT_SYMBOL(foo); [Test Case 3] Preserving an overridden symbol (compile with KBUILD_PRESERVE=1) $ cat foo.c #include <linux/export.h> void foo(void); void foo(void) { } EXPORT_SYMBOL(foo); $ cat foo.symref override foo void foo ( int ) The memory leaks in Test Case 1 and 2 have existed since the introduction of genksyms into the kernel tree. [1] The memory leak in Test Case 3 was introduced by commit 5dae9a550a74 ("genksyms: allow to ignore symbol checksum changes"). When multiple init_declarators are reduced to an init_declarator_list, the decl_spec must be duplicated. Otherwise, the following Test Case 4 would result in a double-free bug. [Test Case 4] $ cat foo.c #include <linux/export.h> extern int foo, bar; int foo, bar; EXPORT_SYMBOL(foo); In this case, 'foo' and 'bar' share the same decl_spec, 'int'. It must be unshared before being passed to add_symbol(). [1]: https://git.kernel.org/pub/scm/linux/kernel/git/history/history.git/commit/?id=46bd1da672d66ccd8a639d3c1f8a166048cca608 Fixes: 5dae9a550a74 ("genksyms: allow to ignore symbol checksum changes") Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 3 +++ scripts/genksyms/parse.y | 14 ++++++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 07f9b8cfb233..8ca46f807b57 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -239,6 +239,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, "unchanged\n"); } sym->is_declared = 1; + free_list(defn, NULL); return sym; } else if (!sym->is_declared) { if (sym->is_override && flag_preserve) { @@ -247,6 +248,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, print_type_name(type, name); fprintf(stderr, " modversion change\n"); sym->is_declared = 1; + free_list(defn, NULL); return sym; } else { status = is_unknown_symbol(sym) ? @@ -254,6 +256,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, } } else { error_with_pos("redefinition of %s", name); + free_list(defn, NULL); return sym; } break; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 8e9b5e69e8f0..840371d01bf4 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -152,14 +152,19 @@ simple_declaration: ; 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; @@ -170,6 +175,11 @@ init_declarator_list: *$3 = 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; -- cgit v1.2.3 From be2fa44b5180a1f021efb40c55fdf63c249c3209 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:39 +0900 Subject: genksyms: fix memory leak when the same symbol is read from *.symref file When a symbol that is already registered is read again from *.symref file, __add_symbol() removes the previous one from the hash table without freeing it. [Test Case] $ cat foo.c #include <linux/export.h> void foo(void); void foo(void) {} EXPORT_SYMBOL(foo); $ cat foo.symref foo void foo ( void ) foo void foo ( void ) When a symbol is removed from the hash table, it must be freed along with its ->name and ->defn members. However, sym->name cannot be freed because it is sometimes shared with node->string, but not always. If sym->name and node->string share the same memory, free(sym->name) could lead to a double-free bug. To resolve this issue, always assign a strdup'ed string to sym->name. Fixes: 64e6c1e12372 ("genksyms: track symbol checksum changes") Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 8 ++++++-- scripts/genksyms/genksyms.h | 2 +- scripts/genksyms/parse.y | 4 ++-- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 8ca46f807b57..c5e8e0e0f949 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -272,11 +272,15 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, 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; @@ -483,7 +487,7 @@ 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); diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 21ed2ec2d98c..5621533dcb8e 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -32,7 +32,7 @@ struct string_list { struct symbol { struct symbol *hash_next; - const char *name; + char *name; enum symbol_type type; struct string_list *defn; struct symbol *expansion_trail; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 840371d01bf4..689cb6bb40b6 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -482,12 +482,12 @@ 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); } -- cgit v1.2.3 From f034d186bf9e2857079815e5490e2810a1a287a6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:40 +0900 Subject: genksyms: reduce the indentation in the for-loop in __add_symbol() To improve readability, reduce the indentation as follows: - Use 'continue' earlier when the symbol does not match - flip !sym->is_declared to flatten the if-else chain No functional changes are intended. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 63 +++++++++++++++++++++------------------------ 1 file changed, 30 insertions(+), 33 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index c5e8e0e0f949..5a90acd693f4 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -226,41 +226,38 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, 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; - free_list(defn, NULL); - 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; - free_list(defn, NULL); - return sym; - } else { - status = is_unknown_symbol(sym) ? - STATUS_DEFINED : STATUS_MODIFIED; - } - } else { - error_with_pos("redefinition of %s", name); - free_list(defn, NULL); - return sym; + if (map_to_ns(sym->type) != map_to_ns(type) || + strcmp(name, sym->name)) + continue; + + 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"); } - break; + sym->is_declared = 1; + free_list(defn, NULL); + return sym; + } else if (sym->is_declared) { + error_with_pos("redefinition of %s", name); + free_list(defn, NULL); + return sym; + } 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; + free_list(defn, NULL); + return sym; + } else { + status = is_unknown_symbol(sym) ? + STATUS_DEFINED : STATUS_MODIFIED; } + break; } if (sym) { -- cgit v1.2.3 From 2480f53f21b21eb24a33815d4623f54fdb30cf27 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:41 +0900 Subject: genksyms: refactor the return points in the for-loop in __add_symbol() free_list() must be called before returning from this for-loop. Swap 'break' and the combination of free_list() and 'return'. This reduces the code and minimizes the risk of introducing memory leaks in future changes. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 5a90acd693f4..41d6cfce0088 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -231,7 +231,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, continue; if (is_reference) { - /* fall through */ ; + break; } else if (sym->type == type && equal_list(sym->defn, defn)) { if (!sym->is_declared && sym->is_override) { print_location(); @@ -239,25 +239,21 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, fprintf(stderr, " modversion is unchanged\n"); } sym->is_declared = 1; - free_list(defn, NULL); - return sym; } else if (sym->is_declared) { error_with_pos("redefinition of %s", name); - free_list(defn, NULL); - return sym; } 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; - free_list(defn, NULL); - return sym; } else { status = is_unknown_symbol(sym) ? STATUS_DEFINED : STATUS_MODIFIED; + break; } - break; + free_list(defn, NULL); + return sym; } if (sym) { -- cgit v1.2.3 From 2759bd908f3cc8d286e1fa64ec7ee7f5d1124837 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:42 +0900 Subject: genksyms: use generic macros for hash table implementation Use macros provided by hashtable.h Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 32 ++++++++++++-------------------- scripts/genksyms/genksyms.h | 4 +++- 2 files changed, 15 insertions(+), 21 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 41d6cfce0088..e2cd3dcb469f 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -18,12 +18,12 @@ #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; @@ -151,14 +151,14 @@ 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; @@ -224,8 +224,8 @@ 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) { + 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; @@ -257,14 +257,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, } if (sym) { - struct symbol **psym; - - for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) { - if (*psym == sym) { - *psym = sym->hash_next; - break; - } - } + hash_del(&sym->hnode); free_list(sym->defn, NULL); free(sym->name); @@ -280,8 +273,7 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, 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; @@ -832,9 +824,9 @@ 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 5621533dcb8e..8c45ada59ece 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -14,6 +14,8 @@ #include <stdio.h> +#include <list_types.h> + enum symbol_type { SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION, SYM_ENUM_CONST @@ -31,7 +33,7 @@ struct string_list { }; struct symbol { - struct symbol *hash_next; + struct hlist_node hnode; char *name; enum symbol_type type; struct string_list *defn; -- cgit v1.2.3 From a56fece7f302ff1eb49535e66bdd5d03ced0ca20 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 3 Jan 2025 16:30:43 +0900 Subject: genksyms: use uint32_t instead of unsigned long for calculating CRC Currently, 'unsigned long' is used for intermediate variables when calculating CRCs. The size of 'long' differs depending on the architecture: it is 32 bits on 32-bit architectures and 64 bits on 64-bit architectures. The CRC values generated by genksyms represent the compatibility of exported symbols. Therefore, reproducibility is important. In other words, we need to ensure that the output is the same when the kernel source is identical, regardless of whether genksyms is running on a 32-bit or 64-bit build machine. Fortunately, the output from genksyms is not affected by the build machine's architecture because only the lower 32 bits of the 'unsigned long' variables are used. To make it even clearer that the CRC calculation is independent of the build machine's architecture, this commit explicitly uses the fixed-width type, uint32_t. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/genksyms/genksyms.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index e2cd3dcb469f..8b0d7ac73dbb 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <string.h> +#include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <assert.h> @@ -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; } @@ -517,7 +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; @@ -624,7 +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); @@ -672,7 +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); } /*----------------------------------------------------------------------*/ -- cgit v1.2.3 From f28568841ae0a0dd48dfc5400aaebedf10a54d10 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:23 +0000 Subject: tools: Add gendwarfksyms Add a basic DWARF parser, which uses libdw to traverse the debugging information in an object file and looks for functions and variables. In follow-up patches, this will be expanded to produce symbol versions for CONFIG_MODVERSIONS from DWARF. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- MAINTAINERS | 7 ++ kernel/module/Kconfig | 8 ++ scripts/Makefile | 1 + scripts/gendwarfksyms/.gitignore | 2 + scripts/gendwarfksyms/Makefile | 8 ++ scripts/gendwarfksyms/dwarf.c | 166 ++++++++++++++++++++++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.c | 128 ++++++++++++++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.h | 95 +++++++++++++++++++ scripts/gendwarfksyms/symbols.c | 98 ++++++++++++++++++++ 9 files changed, 513 insertions(+) create mode 100644 scripts/gendwarfksyms/.gitignore create mode 100644 scripts/gendwarfksyms/Makefile create mode 100644 scripts/gendwarfksyms/dwarf.c create mode 100644 scripts/gendwarfksyms/gendwarfksyms.c create mode 100644 scripts/gendwarfksyms/gendwarfksyms.h create mode 100644 scripts/gendwarfksyms/symbols.c (limited to 'scripts') diff --git a/MAINTAINERS b/MAINTAINERS index 30cbc3d44cd5..1ec4753b1457 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9550,6 +9550,13 @@ W: https://linuxtv.org T: git git://linuxtv.org/media.git F: drivers/media/radio/radio-gemtek* +GENDWARFKSYMS +M: Sami Tolvanen <samitolvanen@google.com> +L: linux-modules@vger.kernel.org +L: linux-kbuild@vger.kernel.org +S: Maintained +F: scripts/gendwarfksyms/ + GENERIC ARCHITECTURE TOPOLOGY M: Sudeep Holla <sudeep.holla@arm.com> L: linux-kernel@vger.kernel.org diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 7b329057997a..4637f063d0fc 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,6 +169,14 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +config GENDWARFKSYMS + bool "gendwarfksyms (from debugging information)" + depends on DEBUG_INFO + # Requires full debugging information, split DWARF not supported. + depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT + # Requires ELF object files. + depends on !LTO + config ASM_MODVERSIONS bool default HAVE_ASM_MODVERSIONS && MODVERSIONS diff --git a/scripts/Makefile b/scripts/Makefile index 6bcda4b9d054..d7fec46d38c0 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -54,6 +54,7 @@ targets += module.lds subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins subdir-$(CONFIG_MODVERSIONS) += genksyms +subdir-$(CONFIG_GENDWARFKSYMS) += gendwarfksyms subdir-$(CONFIG_SECURITY_SELINUX) += selinux subdir-$(CONFIG_SECURITY_IPE) += ipe 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..9f8fec4fd39b --- /dev/null +++ b/scripts/gendwarfksyms/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +hostprogs-always-y += gendwarfksyms + +gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += dwarf.o +gendwarfksyms-objs += symbols.o + +HOSTLDLIBS_gendwarfksyms := -ldw -lelf diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c new file mode 100644 index 000000000000..81df3e2ad3ae --- /dev/null +++ b/scripts/gendwarfksyms/dwarf.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +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; +} + +/* + * Type string processing + */ +static void process(const char *s) +{ + s = s ?: "<null>"; + + if (dump_dies) + fputs(s, stderr); +} + +bool match_all(Dwarf_Die *die) +{ + return true; +} + +int process_die_container(struct state *state, Dwarf_Die *die, + die_callback_t func, die_match_callback_t match) +{ + Dwarf_Die current; + int res; + + res = checkp(dwarf_child(die, ¤t)); + while (!res) { + if (match(¤t)) { + /* <0 = error, 0 = continue, >0 = stop */ + res = checkp(func(state, ¤t)); + if (res) + return res; + } + + res = checkp(dwarf_siblingof(¤t, ¤t)); + } + + return 0; +} + +/* + * Exported symbol processing + */ +static void process_symbol(struct state *state, Dwarf_Die *die, + die_callback_t process_func) +{ + debug("%s", state->sym->name); + check(process_func(state, die)); + if (dump_dies) + fputs("\n", stderr); +} + +static int __process_subprogram(struct state *state, Dwarf_Die *die) +{ + process("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, Dwarf_Die *die) +{ + process("variable "); + return 0; +} + +static void process_variable(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_variable); +} + +static int process_exported_symbols(struct state *unused, 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, 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; + + if (tag == DW_TAG_subprogram) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + return 0; + } + default: + return 0; + } +} + +void process_cu(Dwarf_Die *cudie) +{ + check(process_die_container(NULL, cudie, process_exported_symbols, + match_all)); +} diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c new file mode 100644 index 000000000000..a1d13353c6bc --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -0,0 +1,128 @@ +// 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; + +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" + " -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; + int res; + + debug("%s", name); + dbg = dwfl_module_getdwarf(mod, &dwbias); + + 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); + + 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) +{ + unsigned int n; + int opt; + + static const struct option opts[] = { + { "debug", 0, NULL, 'd' }, + { "dump-dies", 0, &dump_dies, 1 }, + { "help", 0, NULL, 'h' }, + { 0, 0, NULL, 0 } + }; + + while ((opt = getopt_long(argc, argv, "dh", opts, NULL)) != EOF) { + switch (opt) { + case 0: + break; + case 'd': + debug = 1; + break; + case 'h': + usage(); + return 0; + default: + usage(); + return 1; + } + } + + if (optind >= argc) { + usage(); + error("no input files?"); + } + + symbol_read_exports(stdin); + + 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)); + + 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, NULL, 0)) + error("dwfl_getmodules failed for '%s'", argv[n]); + + dwfl_end(dwfl); + } + + symbol_free(); + + return 0; +} diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h new file mode 100644 index 000000000000..5c8288c71fdd --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -0,0 +1,95 @@ +/* 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; + +/* + * 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) + +/* + * 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) + +/* + * symbols.c + */ + +struct symbol { + const char *name; + struct hlist_node name_hash; +}; + +typedef void (*symbol_callback_t)(struct symbol *, void *arg); + +void symbol_read_exports(FILE *file); +struct symbol *symbol_get(const char *name); +void symbol_free(void); + +/* + * dwarf.c + */ + +struct state { + struct symbol *sym; + Dwarf_Die die; +}; + +typedef int (*die_callback_t)(struct state *state, 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, Dwarf_Die *die, + die_callback_t func, die_match_callback_t match); + +void process_cu(Dwarf_Die *cudie); + +#endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c new file mode 100644 index 000000000000..592eacf72694 --- /dev/null +++ b/scripts/gendwarfksyms/symbols.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +#define SYMBOL_HASH_BITS 12 + +/* name -> struct symbol */ +static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS); + +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; + + hash_for_each_possible_safe(symbol_names, match, tmp, name_hash, + hash_str(name)) { + if (strcmp(match->name, name)) + continue; + + if (func) + func(match, data); + + return 1; + } + + return 0; +} + +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; + + 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; + + *res = sym; +} + +struct symbol *symbol_get(const char *name) +{ + struct symbol *sym = NULL; + + for_each(name, get_symbol, &sym); + return sym; +} + +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_names); +} -- cgit v1.2.3 From e982abf43749529687dd1d07fa4f495902910cf2 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:24 +0000 Subject: gendwarfksyms: Add address matching The compiler may choose not to emit type information in DWARF for all aliases, but it's possible for each alias to be exported separately. To ensure we find type information for the aliases as well, read {section, address} tuples from the symbol table and match symbols also by address. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/gendwarfksyms.c | 2 + scripts/gendwarfksyms/gendwarfksyms.h | 13 +++ scripts/gendwarfksyms/symbols.c | 161 ++++++++++++++++++++++++++++++++++ 3 files changed, 176 insertions(+) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index a1d13353c6bc..cd8bfe973a5c 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -105,6 +105,8 @@ int main(int argc, char **argv) error("open failed for '%s': %s", argv[n], strerror(errno)); + symbol_read_symtab(fd); + dwfl = dwfl_begin(&callbacks); if (!dwfl) error("dwfl_begin failed for '%s': %s", argv[n], diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 5c8288c71fdd..cb9fd78a58da 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -63,14 +63,27 @@ extern int dump_dies; * symbols.c */ +static inline unsigned int addr_hash(uintptr_t addr) +{ + return hash_ptr((const void *)addr); +} + +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; }; typedef void (*symbol_callback_t)(struct symbol *, void *arg); void symbol_read_exports(FILE *file); +void symbol_read_symtab(int fd); struct symbol *symbol_get(const char *name); void symbol_free(void); diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c index 592eacf72694..98febb524dd5 100644 --- a/scripts/gendwarfksyms/symbols.c +++ b/scripts/gendwarfksyms/symbols.c @@ -7,9 +7,38 @@ #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; +} + static unsigned int for_each(const char *name, symbol_callback_t func, void *data) { @@ -24,9 +53,13 @@ static unsigned int for_each(const char *name, symbol_callback_t func, 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; } @@ -58,6 +91,7 @@ void symbol_read_exports(FILE *file) sym = xcalloc(1, sizeof(struct symbol)); sym->name = name; + sym->addr.section = SHN_UNDEF; hash_add(symbol_names, &sym->name_hash, hash_str(sym->name)); ++nsym; @@ -84,6 +118,132 @@ struct symbol *symbol_get(const char *name) return sym; } +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_free(void) { struct hlist_node *tmp; @@ -94,5 +254,6 @@ void symbol_free(void) free(sym); } + hash_init(symbol_addrs); hash_init(symbol_names); } -- cgit v1.2.3 From 5b7780e86857f70249df2c4f8982cad3ba931eee Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:25 +0000 Subject: gendwarfksyms: Expand base_type Start making gendwarfksyms more useful by adding support for expanding DW_TAG_base_type types and basic DWARF attributes. Example: $ echo loops_per_jiffy | \ scripts/gendwarfksyms/gendwarfksyms \ --debug --dump-dies vmlinux.o ... gendwarfksyms: process_symbol: loops_per_jiffy variable base_type unsigned long byte_size(8) encoding(7) ... Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 160 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 160 insertions(+) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 81df3e2ad3ae..74e75b8ec891 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -3,8 +3,21 @@ * Copyright (C) 2024 Google LLC */ +#include <inttypes.h> +#include <stdarg.h> #include "gendwarfksyms.h" +#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(udata, Dwarf_Word) + static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value) { Dwarf_Attribute da; @@ -67,6 +80,109 @@ static void process(const char *s) fputs(s, stderr); } +#define MAX_FMT_BUFFER_SIZE 128 + +static void process_fmt(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(buf); + va_end(args); +} + +#define MAX_FQN_SIZE 64 + +/* Get a fully qualified name from DWARF scopes */ +static char *get_fqn(Dwarf_Die *die) +{ + const char *list[MAX_FQN_SIZE]; + Dwarf_Die *scopes = NULL; + bool has_name = false; + char *fqn = NULL; + char *p; + int count = 0; + int len = 0; + int res; + int i; + + res = checkp(dwarf_getscopes_die(die, &scopes)); + if (!res) { + list[count] = get_name_attr(die); + + if (!list[count]) + return NULL; + + len += strlen(list[count]); + count++; + + goto done; + } + + for (i = res - 1; i >= 0 && count < MAX_FQN_SIZE; i--) { + if (dwarf_tag(&scopes[i]) == DW_TAG_compile_unit) + continue; + + list[count] = get_name_attr(&scopes[i]); + + if (list[count]) { + has_name = true; + } else { + list[count] = "<anonymous>"; + has_name = false; + } + + len += strlen(list[count]); + count++; + + if (i > 0) { + list[count++] = "::"; + len += 2; + } + } + + free(scopes); + + if (count == MAX_FQN_SIZE) + warn("increase MAX_FQN_SIZE: reached the maximum"); + + /* Consider the DIE unnamed if the last scope doesn't have a name */ + if (!has_name) + return NULL; +done: + fqn = xmalloc(len + 1); + *fqn = '\0'; + + p = fqn; + for (i = 0; i < count; i++) + p = stpcpy(p, list[i]); + + return fqn; +} + +static void process_fqn(Dwarf_Die *die) +{ + process(" "); + process(get_fqn(die) ?: ""); +} + +#define DEFINE_PROCESS_UDATA_ATTRIBUTE(attribute) \ + static void process_##attribute##_attr(Dwarf_Die *die) \ + { \ + Dwarf_Word value; \ + if (get_udata_attr(die, DW_AT_##attribute, &value)) \ + process_fmt(" " #attribute "(%" PRIu64 ")", value); \ + } + +DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment) +DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) + bool match_all(Dwarf_Die *die) { return true; @@ -93,6 +209,49 @@ int process_die_container(struct state *state, Dwarf_Die *die, return 0; } +static int process_type(struct state *state, Dwarf_Die *die); + +static void process_type_attr(struct state *state, Dwarf_Die *die) +{ + Dwarf_Die type; + + if (get_ref_die_attr(die, DW_AT_type, &type)) { + check(process_type(state, &type)); + return; + } + + /* Compilers can omit DW_AT_type -- print out 'void' to clarify */ + process("base_type void"); +} + +static void process_base_type(struct state *state, Dwarf_Die *die) +{ + process("base_type"); + process_fqn(die); + process_byte_size_attr(die); + process_encoding_attr(die); + process_alignment_attr(die); +} + +#define PROCESS_TYPE(type) \ + case DW_TAG_##type##_type: \ + process_##type##_type(state, die); \ + break; + +static int process_type(struct state *state, Dwarf_Die *die) +{ + int tag = dwarf_tag(die); + + switch (tag) { + PROCESS_TYPE(base) + default: + debug("unimplemented type: %x", tag); + break; + } + + return 0; +} + /* * Exported symbol processing */ @@ -119,6 +278,7 @@ static void process_subprogram(struct state *state, Dwarf_Die *die) static int __process_variable(struct state *state, Dwarf_Die *die) { process("variable "); + process_type_attr(state, die); return 0; } -- cgit v1.2.3 From 0c1c76274e88c420779c3aea077f9812bd16edaa Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:26 +0000 Subject: gendwarfksyms: Add a cache for processed DIEs Basic types in DWARF repeat frequently and traversing the DIEs using libdw is relatively slow. Add a simple hashtable based cache for the processed DIEs. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/Makefile | 1 + scripts/gendwarfksyms/die.c | 143 ++++++++++++++++++++++++++++++++++ scripts/gendwarfksyms/dwarf.c | 136 +++++++++++++++++++++++--------- scripts/gendwarfksyms/gendwarfksyms.c | 6 ++ scripts/gendwarfksyms/gendwarfksyms.h | 63 ++++++++++++++- 5 files changed, 308 insertions(+), 41 deletions(-) create mode 100644 scripts/gendwarfksyms/die.c (limited to 'scripts') diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile index 9f8fec4fd39b..c0d4ce50fc27 100644 --- a/scripts/gendwarfksyms/Makefile +++ b/scripts/gendwarfksyms/Makefile @@ -2,6 +2,7 @@ hostprogs-always-y += gendwarfksyms gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += die.o gendwarfksyms-objs += dwarf.o gendwarfksyms-objs += symbols.o diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c new file mode 100644 index 000000000000..b7d900c6a9c8 --- /dev/null +++ b/scripts/gendwarfksyms/die.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <string.h> +#include "gendwarfksyms.h" + +#define DIE_HASH_BITS 15 + +/* {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->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_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_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 index 74e75b8ec891..f40e23a547da 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -72,17 +72,19 @@ static bool match_export_symbol(struct state *state, Dwarf_Die *die) /* * Type string processing */ -static void process(const char *s) +static void process(struct die *cache, const char *s) { s = s ?: "<null>"; if (dump_dies) fputs(s, stderr); + + die_map_add_string(cache, s); } #define MAX_FMT_BUFFER_SIZE 128 -static void process_fmt(const char *fmt, ...) +static void process_fmt(struct die *cache, const char *fmt, ...) { char buf[MAX_FMT_BUFFER_SIZE]; va_list args; @@ -92,7 +94,7 @@ static void process_fmt(const char *fmt, ...) if (checkp(vsnprintf(buf, sizeof(buf), fmt, args)) >= sizeof(buf)) error("vsnprintf overflow: increase MAX_FMT_BUFFER_SIZE"); - process(buf); + process(cache, buf); va_end(args); } @@ -165,18 +167,28 @@ done: return fqn; } -static void process_fqn(Dwarf_Die *die) +static void update_fqn(struct die *cache, Dwarf_Die *die) +{ + if (!cache->fqn) + cache->fqn = get_fqn(die) ?: ""; +} + +static void process_fqn(struct die *cache, Dwarf_Die *die) { - process(" "); - process(get_fqn(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(Dwarf_Die *die) \ - { \ - Dwarf_Word value; \ - if (get_udata_attr(die, DW_AT_##attribute, &value)) \ - process_fmt(" " #attribute "(%" PRIu64 ")", value); \ +#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(alignment) @@ -188,8 +200,9 @@ bool match_all(Dwarf_Die *die) return true; } -int process_die_container(struct state *state, Dwarf_Die *die, - die_callback_t func, die_match_callback_t match) +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; @@ -198,7 +211,7 @@ int process_die_container(struct state *state, Dwarf_Die *die, while (!res) { if (match(¤t)) { /* <0 = error, 0 = continue, >0 = stop */ - res = checkp(func(state, ¤t)); + res = checkp(func(state, cache, ¤t)); if (res) return res; } @@ -209,39 +222,78 @@ int process_die_container(struct state *state, Dwarf_Die *die, return 0; } -static int process_type(struct state *state, Dwarf_Die *die); +static int process_type(struct state *state, struct die *parent, + Dwarf_Die *die); -static void process_type_attr(struct state *state, 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, &type)); + check(process_type(state, cache, &type)); return; } /* Compilers can omit DW_AT_type -- print out 'void' to clarify */ - process("base_type void"); + process(cache, "base_type void"); +} + +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_base_type(struct state *state, Dwarf_Die *die) +static void process_cached(struct state *state, struct die *cache, + Dwarf_Die *die) { - process("base_type"); - process_fqn(die); - process_byte_size_attr(die); - process_encoding_attr(die); - process_alignment_attr(die); + struct die_fragment *df; + Dwarf_Die child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + process(NULL, df->data.str); + 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"); + check(process_type(state, NULL, &child)); + break; + default: + error("empty die_fragment"); + } + } } -#define PROCESS_TYPE(type) \ - case DW_TAG_##type##_type: \ - process_##type##_type(state, die); \ +#define PROCESS_TYPE(type) \ + case DW_TAG_##type##_type: \ + process_##type##_type(state, cache, die); \ break; -static int process_type(struct state *state, Dwarf_Die *die) +static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) { + struct die *cache; int tag = dwarf_tag(die); + /* + * If we have the DIE already cached, use it instead of walking + * through DWARF. + */ + cache = die_map_get(die, DIE_COMPLETE); + + if (cache->state == DIE_COMPLETE) { + process_cached(state, cache, die); + die_map_add_die(parent, cache); + return 0; + } + switch (tag) { PROCESS_TYPE(base) default: @@ -249,6 +301,11 @@ static int process_type(struct state *state, Dwarf_Die *die) break; } + /* Update cache state and append to the parent (if any) */ + cache->tag = tag; + cache->state = DIE_COMPLETE; + die_map_add_die(parent, cache); + return 0; } @@ -259,14 +316,15 @@ static void process_symbol(struct state *state, Dwarf_Die *die, die_callback_t process_func) { debug("%s", state->sym->name); - check(process_func(state, die)); + check(process_func(state, NULL, die)); if (dump_dies) fputs("\n", stderr); } -static int __process_subprogram(struct state *state, Dwarf_Die *die) +static int __process_subprogram(struct state *state, struct die *cache, + Dwarf_Die *die) { - process("subprogram"); + process(cache, "subprogram"); return 0; } @@ -275,10 +333,11 @@ static void process_subprogram(struct state *state, Dwarf_Die *die) process_symbol(state, die, __process_subprogram); } -static int __process_variable(struct state *state, Dwarf_Die *die) +static int __process_variable(struct state *state, struct die *cache, + Dwarf_Die *die) { - process("variable "); - process_type_attr(state, die); + process(cache, "variable "); + process_type_attr(state, cache, die); return 0; } @@ -287,7 +346,8 @@ static void process_variable(struct state *state, Dwarf_Die *die) process_symbol(state, die, __process_variable); } -static int process_exported_symbols(struct state *unused, Dwarf_Die *die) +static int process_exported_symbols(struct state *unused, struct die *cache, + Dwarf_Die *die) { int tag = dwarf_tag(die); @@ -297,7 +357,7 @@ static int process_exported_symbols(struct state *unused, Dwarf_Die *die) case DW_TAG_class_type: case DW_TAG_structure_type: return check(process_die_container( - NULL, die, process_exported_symbols, match_all)); + NULL, cache, die, process_exported_symbols, match_all)); /* Possible exported symbols */ case DW_TAG_subprogram: @@ -321,6 +381,6 @@ static int process_exported_symbols(struct state *unused, Dwarf_Die *die) void process_cu(Dwarf_Die *cudie) { - check(process_die_container(NULL, cudie, process_exported_symbols, + check(process_die_container(NULL, NULL, cudie, process_exported_symbols, match_all)); } diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index cd8bfe973a5c..3809db840c06 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -43,6 +43,10 @@ static int process_module(Dwfl_Module *mod, void **userdata, const char *name, 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) @@ -53,6 +57,8 @@ static int process_module(Dwfl_Module *mod, void **userdata, const char *name, process_cu(&cudie); } while (cu); + die_map_free(); + return DWARF_CB_OK; } diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index cb9fd78a58da..601f877bc8ca 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -87,6 +87,61 @@ void symbol_read_symtab(int fd); struct symbol *symbol_get(const char *name); void symbol_free(void); +/* + * die.c + */ + +enum die_state { + DIE_INCOMPLETE, + DIE_COMPLETE, + DIE_LAST = DIE_COMPLETE +}; + +enum die_fragment_type { + FRAGMENT_EMPTY, + FRAGMENT_STRING, + FRAGMENT_DIE +}; + +struct die_fragment { + enum die_fragment_type type; + union { + char *str; + 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_COMPLETE) + } + + error("unexpected die_state: %d", state); +} + +struct die { + enum die_state state; + char *fqn; + int tag; + uintptr_t addr; + struct list_head fragments; + struct hlist_node hash; +}; + +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_add_die(struct die *pd, struct die *child); +void die_map_free(void); + /* * dwarf.c */ @@ -96,12 +151,14 @@ struct state { Dwarf_Die die; }; -typedef int (*die_callback_t)(struct state *state, Dwarf_Die *die); +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, Dwarf_Die *die, - die_callback_t func, die_match_callback_t match); +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); -- cgit v1.2.3 From 06b8b036ab9c1e70a562705a398bcd271e0b5ebf Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:27 +0000 Subject: gendwarfksyms: Expand type modifiers and typedefs Add support for expanding DWARF type modifiers, such as pointers, const values etc., and typedefs. These types all have DW_AT_type attribute pointing to the underlying type, and thus produce similar output. Also add linebreaks and indentation to debugging output to make it more readable. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/die.c | 12 +++++++ scripts/gendwarfksyms/dwarf.c | 67 +++++++++++++++++++++++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.h | 5 +++ 3 files changed, 84 insertions(+) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c index b7d900c6a9c8..0d70e02d02b5 100644 --- a/scripts/gendwarfksyms/die.c +++ b/scripts/gendwarfksyms/die.c @@ -130,6 +130,18 @@ void die_map_add_string(struct die *cd, const char *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; diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index f40e23a547da..3e08a32b7b16 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -7,6 +7,17 @@ #include <stdarg.h> #include "gendwarfksyms.h" +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) \ @@ -76,6 +87,12 @@ 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); @@ -239,6 +256,40 @@ static void process_type_attr(struct state *state, struct die *cache, process(cache, "base_type void"); } +/* 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(volatile) +DEFINE_PROCESS_TYPE(typedef) + static void process_base_type(struct state *state, struct die *cache, Dwarf_Die *die) { @@ -260,6 +311,9 @@ static void process_cached(struct state *state, struct die *cache, case FRAGMENT_STRING: 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)) @@ -295,7 +349,20 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) } 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) + /* Other types */ PROCESS_TYPE(base) + PROCESS_TYPE(typedef) default: debug("unimplemented type: %x", tag); break; diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 601f877bc8ca..832d05b4fc1c 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -59,6 +59,9 @@ extern int dump_dies; /* Error == negative values */ #define checkp(expr) __check(expr, __res < 0) +/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */ +#define DW_TAG_typedef_type DW_TAG_typedef + /* * symbols.c */ @@ -100,6 +103,7 @@ enum die_state { enum die_fragment_type { FRAGMENT_EMPTY, FRAGMENT_STRING, + FRAGMENT_LINEBREAK, FRAGMENT_DIE }; @@ -107,6 +111,7 @@ struct die_fragment { enum die_fragment_type type; union { char *str; + int linebreak; uintptr_t addr; } data; struct list_head list; -- cgit v1.2.3 From 220a0857f3a89e0dce3fc7c38d981df41c4537a7 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:28 +0000 Subject: gendwarfksyms: Expand subroutine_type Add support for expanding DW_TAG_subroutine_type and the parameters in DW_TAG_formal_parameter. Use this to also expand subprograms. Example output with --dump-dies: subprogram ( formal_parameter pointer_type { const_type { base_type char byte_size(1) encoding(6) } } ) -> base_type unsigned long byte_size(8) encoding(7) Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 84 +++++++++++++++++++++++++++++++++-- scripts/gendwarfksyms/gendwarfksyms.h | 4 ++ 2 files changed, 85 insertions(+), 3 deletions(-) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 3e08a32b7b16..7d8a4eb6c387 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -212,6 +212,15 @@ DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment) DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size) DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) +/* 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(formal_parameter) + bool match_all(Dwarf_Die *die) { return true; @@ -224,19 +233,28 @@ int process_die_container(struct state *state, struct die *cache, 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) - return res; + goto out; } res = checkp(dwarf_siblingof(¤t, ¤t)); } - return 0; + res = 0; +out: + if (state) + state->first_list_item = false; + + return res; } static int process_type(struct state *state, struct die *parent, @@ -256,6 +274,40 @@ static void process_type_attr(struct state *state, struct die *cache, 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); + + process_list_comma(state, cache); + process(cache, type); + process_type_attr(state, cache, die); + if (name) { + process(cache, " "); + process(cache, name); + } +} + +#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) + /* Container types with DW_AT_type */ static void __process_type(struct state *state, struct die *cache, Dwarf_Die *die, const char *type) @@ -290,6 +342,29 @@ DEFINE_PROCESS_TYPE(shared) DEFINE_PROCESS_TYPE(volatile) DEFINE_PROCESS_TYPE(typedef) +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_base_type(struct state *state, struct die *cache, Dwarf_Die *die) { @@ -360,8 +435,11 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) PROCESS_TYPE(rvalue_reference) PROCESS_TYPE(shared) PROCESS_TYPE(volatile) + /* Subtypes */ + PROCESS_TYPE(formal_parameter) /* Other types */ PROCESS_TYPE(base) + PROCESS_TYPE(subroutine) PROCESS_TYPE(typedef) default: debug("unimplemented type: %x", tag); @@ -391,7 +469,7 @@ static void process_symbol(struct state *state, Dwarf_Die *die, static int __process_subprogram(struct state *state, struct die *cache, Dwarf_Die *die) { - process(cache, "subprogram"); + __process_subroutine_type(state, cache, die, "subprogram"); return 0; } diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 832d05b4fc1c..0746a36f4924 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -60,6 +60,7 @@ extern int dump_dies; #define checkp(expr) __check(expr, __res < 0) /* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */ +#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter #define DW_TAG_typedef_type DW_TAG_typedef /* @@ -154,6 +155,9 @@ void die_map_free(void); struct state { struct symbol *sym; Dwarf_Die die; + + /* List expansion */ + bool first_list_item; }; typedef int (*die_callback_t)(struct state *state, struct die *cache, -- cgit v1.2.3 From c772f1d1eaac608c083ee79fd5cfbe879958eb3e Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:29 +0000 Subject: gendwarfksyms: Expand array_type Add support for expanding DW_TAG_array_type, and the subrange type indicating array size. Example source code: const char *s[34]; Output with --dump-dies: variable array_type[34] { pointer_type { const_type { base_type char byte_size(1) encoding(6) } } byte_size(8) } Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 7d8a4eb6c387..46ce17b2459b 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -220,6 +220,7 @@ DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) } DEFINE_MATCH(formal_parameter) +DEFINE_MATCH(subrange) bool match_all(Dwarf_Die *die) { @@ -342,6 +343,33 @@ DEFINE_PROCESS_TYPE(shared) 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) { @@ -437,7 +465,9 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) PROCESS_TYPE(volatile) /* Subtypes */ PROCESS_TYPE(formal_parameter) + PROCESS_TYPE(subrange) /* Other types */ + PROCESS_TYPE(array) PROCESS_TYPE(base) PROCESS_TYPE(subroutine) PROCESS_TYPE(typedef) -- cgit v1.2.3 From f6bb92455a5e5b2241d2e1f3e240c5fc036c55cb Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:30 +0000 Subject: gendwarfksyms: Expand structure types Recursively expand DWARF structure types, i.e. structs, unions, and enums. Also include relevant DWARF attributes in type strings to encode structure layout, for example. Example output with --dump-dies: subprogram ( formal_parameter structure_type &str { member pointer_type { base_type u8 byte_size(1) encoding(7) } data_ptr data_member_location(0) , member base_type usize byte_size(8) encoding(7) length data_member_location(8) } byte_size(16) alignment(8) msg ) -> base_type void Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 138 +++++++++++++++++++++++++++++++++- scripts/gendwarfksyms/gendwarfksyms.h | 5 ++ 2 files changed, 141 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 46ce17b2459b..6ec1138c459f 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -208,9 +208,14 @@ static void process_fqn(struct die *cache, Dwarf_Die *die) 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) \ @@ -219,7 +224,9 @@ DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) 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) @@ -298,6 +305,10 @@ static void __process_list_type(struct state *state, struct die *cache, 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) \ @@ -308,6 +319,7 @@ static void __process_list_type(struct state *state, struct die *cache, } 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, @@ -340,6 +352,7 @@ 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) @@ -393,6 +406,107 @@ static void process_subroutine_type(struct state *state, struct die *cache, __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 ___process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + switch (dwarf_tag(die)) { + case DW_TAG_member: + 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) +{ + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + + check(process_die_container(state, cache, die, process_func, + match_func)); + + process_linebreak(cache, -1); + process(cache, "}"); + + 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) +DEFINE_PROCESS_STRUCTURE_TYPE(union) + +static void process_enumerator_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Word value; + + process_list_comma(state, cache); + process(cache, "enumerator"); + process_fqn(cache, die); + + if (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) { @@ -403,6 +517,16 @@ static void process_base_type(struct state *state, struct die *cache, 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) { @@ -463,17 +587,27 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) 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: - debug("unimplemented type: %x", tag); - break; + error("unexpected type: %x", tag); } /* Update cache state and append to the parent (if any) */ diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 0746a36f4924..1796f71b3a34 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -60,8 +60,13 @@ extern int dump_dies; #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 -- cgit v1.2.3 From f936c129fd4c3ce495768374ea48e5b736655046 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:31 +0000 Subject: gendwarfksyms: Limit structure expansion Expand each structure type only once per exported symbol. This is necessary to support self-referential structures, which would otherwise result in infinite recursion, and it's sufficient for catching ABI changes. Types defined in .c files are opaque to external users and thus cannot affect the ABI. Consider type definitions in .c files to be declarations to prevent opaque types from changing symbol versions. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/Makefile | 1 + scripts/gendwarfksyms/cache.c | 51 ++++++++++++++ scripts/gendwarfksyms/dwarf.c | 125 +++++++++++++++++++++++++++++++--- scripts/gendwarfksyms/gendwarfksyms.h | 46 +++++++++++++ 4 files changed, 215 insertions(+), 8 deletions(-) create mode 100644 scripts/gendwarfksyms/cache.c (limited to 'scripts') diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile index c0d4ce50fc27..c06145d84df8 100644 --- a/scripts/gendwarfksyms/Makefile +++ b/scripts/gendwarfksyms/Makefile @@ -2,6 +2,7 @@ hostprogs-always-y += gendwarfksyms gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += cache.o gendwarfksyms-objs += die.o gendwarfksyms-objs += dwarf.o gendwarfksyms-objs += symbols.o 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/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 6ec1138c459f..6b30e45a4e82 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -27,6 +27,7 @@ static void process_linebreak(struct die *cache, int n) !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) @@ -80,6 +81,55 @@ static bool match_export_symbol(struct state *state, Dwarf_Die *die) 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(Dwarf_Die *die) +{ + bool value; + + if (get_flag_attr(die, DW_AT_declaration, &value) && value) + return false; + + return !is_definition_private(die); +} + /* * Type string processing */ @@ -456,19 +506,27 @@ static void __process_structure_type(struct state *state, struct die *cache, 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); - check(process_die_container(state, cache, die, process_func, - match_func)); + expand = state->expand.expand && is_kabi_definition(die); + + if (expand) { + check(process_die_container(state, cache, die, process_func, + match_func)); + } process_linebreak(cache, -1); process(cache, "}"); - process_byte_size_attr(cache, die); - process_alignment_attr(cache, die); + if (expand) { + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); + } } #define DEFINE_PROCESS_STRUCTURE_TYPE(structure) \ @@ -553,6 +611,30 @@ static void process_cached(struct state *state, struct die *cache, } } +static void state_init(struct state *state) +{ + state->expand.expand = true; + cache_init(&state->expansion_cache); +} + +static void expansion_state_restore(struct expansion_state *state, + struct expansion_state *saved) +{ + state->expand = saved->expand; +} + +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); \ @@ -560,18 +642,39 @@ static void process_cached(struct state *state, struct die *cache, 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); + /* - * If we have the DIE already cached, use it instead of walking + * 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, DIE_COMPLETE); + cache = die_map_get(die, want_state); - if (cache->state == DIE_COMPLETE) { + if (cache->state == want_state) { process_cached(state, cache, die); die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); return 0; } @@ -612,9 +715,10 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) /* Update cache state and append to the parent (if any) */ cache->tag = tag; - cache->state = DIE_COMPLETE; + cache->state = want_state; die_map_add_die(parent, cache); + expansion_state_restore(&state->expand, &saved); return 0; } @@ -676,11 +780,14 @@ static int process_exported_symbols(struct state *unused, struct die *cache, if (!match_export_symbol(&state, die)) return 0; + state_init(&state); + if (tag == DW_TAG_subprogram) process_subprogram(&state, &state.die); else process_variable(&state, &state.die); + cache_free(&state.expansion_cache); return 0; } default: @@ -692,4 +799,6 @@ void process_cu(Dwarf_Die *cudie) { check(process_die_container(NULL, NULL, cudie, process_exported_symbols, match_all)); + + cache_free(&srcfile_cache); } diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 1796f71b3a34..941c4134da8e 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -102,6 +102,7 @@ void symbol_free(void); enum die_state { DIE_INCOMPLETE, + DIE_UNEXPANDED, DIE_COMPLETE, DIE_LAST = DIE_COMPLETE }; @@ -131,6 +132,7 @@ static inline const char *die_state_name(enum die_state state) { switch (state) { CASE_CONST_TO_STR(DIE_INCOMPLETE) + CASE_CONST_TO_STR(DIE_UNEXPANDED) CASE_CONST_TO_STR(DIE_COMPLETE) } @@ -153,16 +155,60 @@ void die_map_add_linebreak(struct die *pd, int linebreak); 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; +}; + struct state { struct symbol *sym; Dwarf_Die die; /* List expansion */ bool first_list_item; + + /* Structure expansion */ + struct expansion_state expand; + struct cache expansion_cache; }; typedef int (*die_callback_t)(struct state *state, struct die *cache, -- cgit v1.2.3 From d2ffdc1c9a0ee71b30e25fbe3e2a37bf4c146085 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:32 +0000 Subject: gendwarfksyms: Add die_map debugging Debugging the DWARF processing can be somewhat challenging, so add more detailed debugging output for die_map operations. Add the --dump-die-map flag, which adds color coded tags to the output for die_map changes. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 15 +++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.c | 7 +++++++ scripts/gendwarfksyms/gendwarfksyms.h | 13 +++++++++++++ 3 files changed, 35 insertions(+) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 6b30e45a4e82..364ff4892d5c 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -146,6 +146,8 @@ static void process(struct die *cache, const char *s) if (dump_dies) fputs(s, stderr); + if (cache) + die_debug_r("cache %p string '%s'", cache, s); die_map_add_string(cache, s); } @@ -594,6 +596,8 @@ static void process_cached(struct state *state, struct die *cache, 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: @@ -603,6 +607,8 @@ static void process_cached(struct state *state, struct die *cache, 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: @@ -671,6 +677,9 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) 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); @@ -678,6 +687,9 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) 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) @@ -713,6 +725,9 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) 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; diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index 3809db840c06..bf282e33e00c 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -19,6 +19,8 @@ int debug; /* Dump DIE contents */ int dump_dies; +/* Print debugging information about die_map changes */ +int dump_die_map; static void usage(void) { @@ -26,6 +28,7 @@ static void usage(void) "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" " -h, --help Print this message\n" "\n", stderr); @@ -75,6 +78,7 @@ int main(int argc, char **argv) static const struct option opts[] = { { "debug", 0, NULL, 'd' }, { "dump-dies", 0, &dump_dies, 1 }, + { "dump-die-map", 0, &dump_die_map, 1 }, { "help", 0, NULL, 'h' }, { 0, 0, NULL, 0 } }; @@ -95,6 +99,9 @@ int main(int argc, char **argv) } } + if (dump_die_map) + dump_dies = 1; + if (optind >= argc) { usage(); error("no input files?"); diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 941c4134da8e..251832dac599 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -21,6 +21,7 @@ */ extern int debug; extern int dump_dies; +extern int dump_die_map; /* * Output helpers @@ -43,6 +44,18 @@ extern int dump_dies; 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 */ -- cgit v1.2.3 From ab4439981f8549b013f4ea0b274b7c77c88ab4bc Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:33 +0000 Subject: gendwarfksyms: Add symtypes output Add support for producing genksyms-style symtypes files. Process die_map to find the longest expansions for each type, and use symtypes references in type definitions. The basic file format is similar to genksyms, with two notable exceptions: 1. Type names with spaces (common with Rust) in references are wrapped in single quotes. E.g.: s#'core::result::Result<u8, core::num::error::ParseIntError>' 2. The actual type definition is the simple parsed DWARF format we output with --dump-dies, not the preprocessed C-style format genksyms produces. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/Makefile | 1 + scripts/gendwarfksyms/die.c | 11 ++ scripts/gendwarfksyms/dwarf.c | 1 + scripts/gendwarfksyms/gendwarfksyms.c | 33 +++- scripts/gendwarfksyms/gendwarfksyms.h | 19 ++ scripts/gendwarfksyms/symbols.c | 4 +- scripts/gendwarfksyms/types.c | 363 ++++++++++++++++++++++++++++++++++ 7 files changed, 429 insertions(+), 3 deletions(-) create mode 100644 scripts/gendwarfksyms/types.c (limited to 'scripts') diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile index c06145d84df8..6540282dc746 100644 --- a/scripts/gendwarfksyms/Makefile +++ b/scripts/gendwarfksyms/Makefile @@ -6,5 +6,6 @@ gendwarfksyms-objs += cache.o gendwarfksyms-objs += die.o gendwarfksyms-objs += dwarf.o gendwarfksyms-objs += symbols.o +gendwarfksyms-objs += types.o HOSTLDLIBS_gendwarfksyms := -ldw -lelf diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c index 0d70e02d02b5..66bd4c9bc952 100644 --- a/scripts/gendwarfksyms/die.c +++ b/scripts/gendwarfksyms/die.c @@ -22,6 +22,7 @@ static inline unsigned int die_hash(uintptr_t addr, enum die_state state) static void init_die(struct die *cd) { cd->state = DIE_INCOMPLETE; + cd->mapped = false; cd->fqn = NULL; cd->tag = -1; cd->addr = 0; @@ -83,6 +84,16 @@ static void reset_die(struct die *cd) 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; diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 364ff4892d5c..a9966a23167a 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -745,6 +745,7 @@ static void process_symbol(struct state *state, Dwarf_Die *die, { debug("%s", state->sym->name); check(process_func(state, NULL, die)); + state->sym->state = SYMBOL_MAPPED; if (dump_dies) fputs("\n", stderr); } diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index bf282e33e00c..1d30f42cbd14 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -21,6 +21,11 @@ int debug; 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; +/* Write a symtypes file */ +int symtypes; +static const char *symtypes_file; static void usage(void) { @@ -29,6 +34,8 @@ static void usage(void) " -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" + " -T, --symtypes file Write a symtypes file\n" " -h, --help Print this message\n" "\n", stderr); @@ -41,6 +48,7 @@ static int process_module(Dwfl_Module *mod, void **userdata, const char *name, Dwarf_Die cudie; Dwarf_CU *cu = NULL; Dwarf *dbg; + FILE *symfile = arg; int res; debug("%s", name); @@ -60,6 +68,10 @@ static int process_module(Dwfl_Module *mod, void **userdata, const char *name, process_cu(&cudie); } while (cu); + /* + * Use die_map to expand type strings and write them to `symfile`. + */ + generate_symtypes(symfile); die_map_free(); return DWARF_CB_OK; @@ -72,6 +84,7 @@ static const Dwfl_Callbacks callbacks = { int main(int argc, char **argv) { + FILE *symfile = NULL; unsigned int n; int opt; @@ -79,17 +92,23 @@ int main(int argc, char **argv) { "debug", 0, NULL, 'd' }, { "dump-dies", 0, &dump_dies, 1 }, { "dump-die-map", 0, &dump_die_map, 1 }, + { "dump-types", 0, &dump_types, 1 }, + { "symtypes", 1, NULL, 'T' }, { "help", 0, NULL, 'h' }, { 0, 0, NULL, 0 } }; - while ((opt = getopt_long(argc, argv, "dh", opts, NULL)) != EOF) { + while ((opt = getopt_long(argc, argv, "dT:h", opts, NULL)) != EOF) { switch (opt) { case 0: break; case 'd': debug = 1; break; + case 'T': + symtypes = 1; + symtypes_file = optarg; + break; case 'h': usage(); return 0; @@ -109,6 +128,13 @@ int main(int argc, char **argv) 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; @@ -131,12 +157,15 @@ int main(int argc, char **argv) dwfl_report_end(dwfl, NULL, NULL); - if (dwfl_getmodules(dwfl, &process_module, NULL, 0)) + if (dwfl_getmodules(dwfl, &process_module, symfile, 0)) error("dwfl_getmodules failed for '%s'", argv[n]); dwfl_end(dwfl); } + if (symfile) + check(fclose(symfile)); + symbol_free(); return 0; diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 251832dac599..98d5b2315f21 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -22,6 +22,8 @@ extern int debug; extern int dump_dies; extern int dump_die_map; +extern int dump_types; +extern int symtypes; /* * Output helpers @@ -90,6 +92,11 @@ static inline unsigned int addr_hash(uintptr_t addr) return hash_ptr((const void *)addr); } +enum symbol_state { + SYMBOL_UNPROCESSED, + SYMBOL_MAPPED, +}; + struct symbol_addr { uint32_t section; Elf64_Addr address; @@ -100,6 +107,8 @@ struct symbol { struct symbol_addr addr; struct hlist_node addr_hash; struct hlist_node name_hash; + enum symbol_state state; + uintptr_t die_addr; }; typedef void (*symbol_callback_t)(struct symbol *, void *arg); @@ -154,6 +163,7 @@ static inline const char *die_state_name(enum die_state state) struct die { enum die_state state; + bool mapped; char *fqn; int tag; uintptr_t addr; @@ -161,10 +171,13 @@ struct die { 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); @@ -235,4 +248,10 @@ int process_die_container(struct state *state, struct die *cache, void process_cu(Dwarf_Die *cudie); +/* + * types.c + */ + +void generate_symtypes(FILE *file); + #endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c index 98febb524dd5..0d2ce7284a53 100644 --- a/scripts/gendwarfksyms/symbols.c +++ b/scripts/gendwarfksyms/symbols.c @@ -92,6 +92,7 @@ void symbol_read_exports(FILE *file) 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; @@ -107,7 +108,8 @@ static void get_symbol(struct symbol *sym, void *arg) { struct symbol **res = arg; - *res = sym; + if (sym->state == SYMBOL_UNPROCESSED) + *res = sym; } struct symbol *symbol_get(const char *name) diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c new file mode 100644 index 000000000000..21d7a34228eb --- /dev/null +++ b/scripts/gendwarfksyms/types.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <inttypes.h> +#include <stdio.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); +} + +/* + * 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 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->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 __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); +} + +void generate_symtypes(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. If a symtypes file is requested, write type_map contents to + * the file. + */ + type_map_write(file); + type_map_free(); +} -- cgit v1.2.3 From 71378888018833a1cdcbf72f1e95d7c010542d8b Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:34 +0000 Subject: gendwarfksyms: Add symbol versioning Calculate symbol versions from the fully expanded type strings in type_map, and output the versions in a genksyms-compatible format. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/Makefile | 2 +- scripts/gendwarfksyms/dwarf.c | 25 ++++++- scripts/gendwarfksyms/gendwarfksyms.c | 10 ++- scripts/gendwarfksyms/gendwarfksyms.h | 13 +++- scripts/gendwarfksyms/symbols.c | 53 +++++++++++++++ scripts/gendwarfksyms/types.c | 122 +++++++++++++++++++++++++++++++++- 6 files changed, 216 insertions(+), 9 deletions(-) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile index 6540282dc746..e889b958957b 100644 --- a/scripts/gendwarfksyms/Makefile +++ b/scripts/gendwarfksyms/Makefile @@ -8,4 +8,4 @@ gendwarfksyms-objs += dwarf.o gendwarfksyms-objs += symbols.o gendwarfksyms-objs += types.o -HOSTLDLIBS_gendwarfksyms := -ldw -lelf +HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index a9966a23167a..bdf899d60707 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -740,12 +740,33 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) /* * 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, NULL, die)); - state->sym->state = SYMBOL_MAPPED; + check(process_func(state, cache, die)); + cache->state = DIE_SYMBOL; if (dump_dies) fputs("\n", stderr); } diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index 1d30f42cbd14..b0e13c37c6c2 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -23,6 +23,8 @@ int dump_dies; 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; /* Write a symtypes file */ int symtypes; static const char *symtypes_file; @@ -35,6 +37,7 @@ static void usage(void) " --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" " -T, --symtypes file Write a symtypes file\n" " -h, --help Print this message\n" "\n", @@ -69,9 +72,10 @@ static int process_module(Dwfl_Module *mod, void **userdata, const char *name, } while (cu); /* - * Use die_map to expand type strings and write them to `symfile`. + * Use die_map to expand type strings, write them to `symfile`, and + * calculate symbol versions. */ - generate_symtypes(symfile); + generate_symtypes_and_versions(symfile); die_map_free(); return DWARF_CB_OK; @@ -93,6 +97,7 @@ int main(int argc, char **argv) { "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 }, { "symtypes", 1, NULL, 'T' }, { "help", 0, NULL, 'h' }, { 0, 0, NULL, 0 } @@ -166,6 +171,7 @@ int main(int argc, char **argv) if (symfile) check(fclose(symfile)); + symbol_print_versions(); symbol_free(); return 0; diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 98d5b2315f21..203534abcd35 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -23,6 +23,7 @@ extern int debug; extern int dump_dies; extern int dump_die_map; extern int dump_types; +extern int dump_versions; extern int symtypes; /* @@ -95,6 +96,7 @@ static inline unsigned int addr_hash(uintptr_t addr) enum symbol_state { SYMBOL_UNPROCESSED, SYMBOL_MAPPED, + SYMBOL_PROCESSED }; struct symbol_addr { @@ -109,6 +111,7 @@ struct symbol { struct hlist_node name_hash; enum symbol_state state; uintptr_t die_addr; + unsigned long crc; }; typedef void (*symbol_callback_t)(struct symbol *, void *arg); @@ -116,6 +119,10 @@ typedef void (*symbol_callback_t)(struct symbol *, void *arg); void symbol_read_exports(FILE *file); void symbol_read_symtab(int fd); struct symbol *symbol_get(const char *name); +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); /* @@ -126,7 +133,8 @@ enum die_state { DIE_INCOMPLETE, DIE_UNEXPANDED, DIE_COMPLETE, - DIE_LAST = DIE_COMPLETE + DIE_SYMBOL, + DIE_LAST = DIE_SYMBOL }; enum die_fragment_type { @@ -156,6 +164,7 @@ static inline const char *die_state_name(enum die_state state) CASE_CONST_TO_STR(DIE_INCOMPLETE) CASE_CONST_TO_STR(DIE_UNEXPANDED) CASE_CONST_TO_STR(DIE_COMPLETE) + CASE_CONST_TO_STR(DIE_SYMBOL) } error("unexpected die_state: %d", state); @@ -252,6 +261,6 @@ void process_cu(Dwarf_Die *cudie); * types.c */ -void generate_symtypes(FILE *file); +void generate_symtypes_and_versions(FILE *file); #endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c index 0d2ce7284a53..4c499ba6c86d 100644 --- a/scripts/gendwarfksyms/symbols.c +++ b/scripts/gendwarfksyms/symbols.c @@ -66,6 +66,36 @@ static unsigned int for_each(const char *name, symbol_callback_t func, 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_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; @@ -120,6 +150,16 @@ struct symbol *symbol_get(const char *name) 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); @@ -246,6 +286,19 @@ 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; diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c index 21d7a34228eb..6c03265f4d10 100644 --- a/scripts/gendwarfksyms/types.c +++ b/scripts/gendwarfksyms/types.c @@ -6,6 +6,7 @@ #define _GNU_SOURCE #include <inttypes.h> #include <stdio.h> +#include <zlib.h> #include "gendwarfksyms.h" @@ -178,6 +179,33 @@ static void type_map_free(void) 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 @@ -187,6 +215,12 @@ static void type_map_free(void) * * 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) { @@ -214,6 +248,8 @@ static char *get_type_name(struct die *cache) warn("found incomplete cache entry: %p", cache); return NULL; } + if (cache->state == DIE_SYMBOL) + return NULL; if (!cache->fqn || !*cache->fqn) return NULL; @@ -231,6 +267,39 @@ static char *get_type_name(struct die *cache) 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); @@ -337,7 +406,49 @@ static void expand_type(struct die *cache, void *arg) free(name); } -void generate_symtypes(FILE *file) +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); @@ -355,7 +466,14 @@ void generate_symtypes(FILE *file) die_map_for_each(expand_type, NULL); /* - * 2. If a symtypes file is requested, write type_map contents to + * 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); -- cgit v1.2.3 From 936cf61c3ef5d6dad714d6c01a85704027dddeb9 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:35 +0000 Subject: gendwarfksyms: Add support for kABI rules Distributions that want to maintain a stable kABI need the ability to make ABI compatible changes to kernel without affecting symbol versions, either because of LTS updates or backports. With genksyms, developers would typically hide these changes from version calculation with #ifndef __GENKSYMS__, which would result in the symbol version not changing even though the actual type has changed. When we process precompiled object files, this isn't an option. To support this use case, add a --stable command line flag that gates kABI stability features that are not needed in mainline kernels, but can be useful for distributions, and add support for kABI rules, which can be used to restrict gendwarfksyms output. The rules are specified as a set of null-terminated strings stored in the .discard.gendwarfksyms.kabi_rules section. Each rule consists of four strings as follows: "version\0type\0target\0value" The version string ensures the structure can be changed in a backwards compatible way. The type string indicates the type of the rule, and target and value strings contain rule-specific data. Initially support two simple rules: 1. Declaration-only types A type declaration can change into a full definition when additional includes are pulled in to the TU, which changes the versions of any symbol that references the type. Add support for defining declaration-only types whose definition is not expanded during versioning. 2. Ignored enumerators It's possible to add new enum fields without changing the ABI, but as the fields are included in symbol versioning, this would change the versions. Add support for ignoring specific fields. 3. Overridden enumerator values Add support for overriding enumerator values when calculating versions. This may be needed when the last field of the enum is used as a sentinel and new fields must be added before it. Add examples for using the rules under the examples/ directory. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/Makefile | 1 + scripts/gendwarfksyms/dwarf.c | 25 ++- scripts/gendwarfksyms/examples/kabi.h | 70 +++++++ scripts/gendwarfksyms/examples/kabi_ex.c | 14 ++ scripts/gendwarfksyms/examples/kabi_ex.h | 64 ++++++ scripts/gendwarfksyms/gendwarfksyms.c | 11 +- scripts/gendwarfksyms/gendwarfksyms.h | 14 ++ scripts/gendwarfksyms/kabi.c | 336 +++++++++++++++++++++++++++++++ 8 files changed, 531 insertions(+), 4 deletions(-) create mode 100644 scripts/gendwarfksyms/examples/kabi.h create mode 100644 scripts/gendwarfksyms/examples/kabi_ex.c create mode 100644 scripts/gendwarfksyms/examples/kabi_ex.h create mode 100644 scripts/gendwarfksyms/kabi.c (limited to 'scripts') diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile index e889b958957b..6334c7d3c4d5 100644 --- a/scripts/gendwarfksyms/Makefile +++ b/scripts/gendwarfksyms/Makefile @@ -5,6 +5,7 @@ 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 diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index bdf899d60707..17f7e6b9a7ff 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -120,13 +120,16 @@ static bool is_definition_private(Dwarf_Die *die) return !!res; } -static bool is_kabi_definition(Dwarf_Die *die) +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); } @@ -515,9 +518,10 @@ static void __process_structure_type(struct state *state, struct die *cache, process(cache, " {"); process_linebreak(cache, 1); - expand = state->expand.expand && is_kabi_definition(die); + 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)); } @@ -548,13 +552,26 @@ DEFINE_PROCESS_STRUCTURE_TYPE(union) 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 (get_udata_attr(die, DW_AT_const_value, &value)) { + if (overridden || get_udata_attr(die, DW_AT_const_value, &value)) { process(cache, " = "); process_fmt(cache, "%" PRIu64, value); } @@ -620,6 +637,7 @@ static void process_cached(struct state *state, struct die *cache, static void state_init(struct state *state) { state->expand.expand = true; + state->expand.current_fqn = NULL; cache_init(&state->expansion_cache); } @@ -627,6 +645,7 @@ 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, diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h new file mode 100644 index 000000000000..fcd0300e5b58 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi.h @@ -0,0 +1,70 @@ +/* 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 + +/* + * 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) + +#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..799552ea6679 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.c @@ -0,0 +1,14 @@ +// 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; diff --git a/scripts/gendwarfksyms/examples/kabi_ex.h b/scripts/gendwarfksyms/examples/kabi_ex.h new file mode 100644 index 000000000000..fca1e07c78e2 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.h @@ -0,0 +1,64 @@ +/* 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) + */ + +#endif /* __KABI_EX_H__ */ diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index b0e13c37c6c2..08ae61eb327e 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -25,6 +25,8 @@ int dump_die_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; @@ -38,6 +40,7 @@ static void usage(void) " --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", @@ -98,18 +101,22 @@ int main(int argc, char **argv) { "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, "dT:h", opts, NULL)) != EOF) { + 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; @@ -150,6 +157,7 @@ int main(int argc, char **argv) strerror(errno)); symbol_read_symtab(fd); + kabi_read_rules(fd); dwfl = dwfl_begin(&callbacks); if (!dwfl) @@ -166,6 +174,7 @@ int main(int argc, char **argv) error("dwfl_getmodules failed for '%s'", argv[n]); dwfl_end(dwfl); + kabi_free(); } if (symfile) diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index 203534abcd35..c0207ca10e19 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -24,6 +24,7 @@ extern int dump_dies; extern int dump_die_map; extern int dump_types; extern int dump_versions; +extern int stable; extern int symtypes; /* @@ -232,6 +233,7 @@ static inline bool cache_was_expanded(struct cache *cache, void *addr) struct expansion_state { bool expand; + const char *current_fqn; }; struct state { @@ -263,4 +265,16 @@ void process_cu(Dwarf_Die *cudie); 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); +} -- cgit v1.2.3 From a93694188127a5f7ba3baa2f98b275ce388a5246 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:36 +0000 Subject: gendwarfksyms: Add support for reserved and ignored fields Distributions that want to maintain a stable kABI need the ability to make ABI compatible changes to kernel data structures without affecting symbol versions, either because of LTS updates or backports. With genksyms, developers would typically hide these changes from version calculation with #ifndef __GENKSYMS__, which would result in the symbol version not changing even though the actual type has changed. When we process precompiled object files, this isn't an option. Change union processing to recognize field name prefixes that allow the user to ignore the union completely during symbol versioning with a __kabi_ignored prefix in a field name, or to replace the type of a placeholder field using a __kabi_reserved field name prefix. For example, assume we want to add a new field to an existing alignment hole in a data structure, and ignore the new field when calculating symbol versions: struct struct1 { int a; /* a 4-byte alignment hole */ unsigned long b; }; To add `int n` to the alignment hole, we can add a union that includes a __kabi_ignored field that causes gendwarfksyms to ignore the entire union: struct struct1 { int a; union { char __kabi_ignored_0; int n; }; unsigned long b; }; With --stable, both structs produce the same symbol version. Alternatively, when a distribution expects future modification to a data structure, they can explicitly add reserved fields: struct struct2 { long a; long __kabi_reserved_0; /* reserved for future use */ }; To take the field into use, we can again replace it with a union, with one of the fields keeping the __kabi_reserved name prefix to indicate the original type: struct struct2 { long a; union { long __kabi_reserved_0; struct { int b; int v; }; }; Here gendwarfksyms --stable replaces the union with the type of the placeholder field when calculating versions. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 248 ++++++++++++++++++++++++++++++- scripts/gendwarfksyms/examples/kabi.h | 87 +++++++++++ scripts/gendwarfksyms/examples/kabi_ex.c | 16 ++ scripts/gendwarfksyms/examples/kabi_ex.h | 199 +++++++++++++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.h | 9 ++ 5 files changed, 558 insertions(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 17f7e6b9a7ff..746a89d9e3d4 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -3,10 +3,33 @@ * Copyright (C) 2024 Google LLC */ +#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; @@ -353,13 +376,23 @@ static void __process_list_type(struct state *state, struct die *cache, { 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); @@ -486,11 +519,208 @@ static void process_variant_part_type(struct state *state, struct die *cache, 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: @@ -547,7 +777,23 @@ static void __process_structure_type(struct state *state, struct die *cache, DEFINE_PROCESS_STRUCTURE_TYPE(class) DEFINE_PROCESS_STRUCTURE_TYPE(structure) -DEFINE_PROCESS_STRUCTURE_TYPE(union) + +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) diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h index fcd0300e5b58..97a5669b083d 100644 --- a/scripts/gendwarfksyms/examples/kabi.h +++ b/scripts/gendwarfksyms/examples/kabi.h @@ -43,6 +43,28 @@ __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 @@ -67,4 +89,69 @@ #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 index 799552ea6679..0b7ffd830541 100644 --- a/scripts/gendwarfksyms/examples/kabi_ex.c +++ b/scripts/gendwarfksyms/examples/kabi_ex.c @@ -12,3 +12,19 @@ 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 index fca1e07c78e2..1736e0f65208 100644 --- a/scripts/gendwarfksyms/examples/kabi_ex.h +++ b/scripts/gendwarfksyms/examples/kabi_ex.h @@ -59,6 +59,205 @@ KABI_ENUMERATOR_VALUE(e, D, 123456789); * 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/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index c0207ca10e19..fe49730fe623 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -236,6 +236,12 @@ struct expansion_state { const char *current_fqn; }; +struct kabi_state { + int members; + Dwarf_Die placeholder; + const char *orig_name; +}; + struct state { struct symbol *sym; Dwarf_Die die; @@ -246,6 +252,9 @@ struct state { /* 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, -- cgit v1.2.3 From fa624569b70d8015775592ae7e2c514009367541 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:37 +0000 Subject: gendwarfksyms: Add support for symbol type pointers The compiler may choose not to emit type information in DWARF for external symbols. Clang, for example, does this for symbols not defined in the current TU. To provide a way to work around this issue, add support for __gendwarfksyms_ptr_<symbol> pointers that force the compiler to emit the necessary type information in DWARF also for the missing symbols. Example usage: #define GENDWARFKSYMS_PTR(sym) \ static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ __section(".discard.gendwarfksyms") = &sym; extern int external_symbol(void); GENDWARFKSYMS_PTR(external_symbol); Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Petr Pavlu <petr.pavlu@suse.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/gendwarfksyms/dwarf.c | 55 +++++++++++++++++++++++++++++- scripts/gendwarfksyms/examples/symbolptr.c | 33 ++++++++++++++++++ scripts/gendwarfksyms/gendwarfksyms.h | 7 ++++ scripts/gendwarfksyms/symbols.c | 27 +++++++++++++++ 4 files changed, 121 insertions(+), 1 deletion(-) create mode 100644 scripts/gendwarfksyms/examples/symbolptr.c (limited to 'scripts') diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c index 746a89d9e3d4..534d9aa7c114 100644 --- a/scripts/gendwarfksyms/dwarf.c +++ b/scripts/gendwarfksyms/dwarf.c @@ -1061,6 +1061,31 @@ 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) { @@ -1084,7 +1109,9 @@ static int process_exported_symbols(struct state *unused, struct die *cache, state_init(&state); - if (tag == DW_TAG_subprogram) + 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); @@ -1097,10 +1124,36 @@ static int process_exported_symbols(struct state *unused, struct die *cache, } } +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); +} + void process_cu(Dwarf_Die *cudie) { 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/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.h b/scripts/gendwarfksyms/gendwarfksyms.h index fe49730fe623..197a1a8123c6 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -89,6 +89,10 @@ extern int symtypes; * 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); @@ -112,14 +116,17 @@ struct symbol { 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); diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c index 4c499ba6c86d..327f87389c34 100644 --- a/scripts/gendwarfksyms/symbols.c +++ b/scripts/gendwarfksyms/symbols.c @@ -39,6 +39,20 @@ static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func, 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) { @@ -47,6 +61,8 @@ static unsigned int for_each(const char *name, symbol_callback_t func, 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)) { @@ -84,6 +100,17 @@ void symbol_set_crc(struct symbol *sym, unsigned long crc) 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; -- cgit v1.2.3 From 9c3681f9b9fd12cdbc4a542df599f1837512f3d5 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen <samitolvanen@google.com> Date: Fri, 3 Jan 2025 20:45:39 +0000 Subject: kbuild: Add gendwarfksyms as an alternative to genksyms When MODVERSIONS is enabled, allow selecting gendwarfksyms as the implementation, but default to genksyms. Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- kernel/module/Kconfig | 22 ++++++++++++++++++++++ scripts/Makefile | 2 +- scripts/Makefile.build | 35 +++++++++++++++++++++++++++++------ 3 files changed, 52 insertions(+), 7 deletions(-) (limited to 'scripts') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 4637f063d0fc..d443fc504ffc 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,6 +169,22 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +choice + prompt "Module versioning implementation" + depends on MODVERSIONS + help + Select the tool used to calculate symbol versions for modules. + + If unsure, select GENKSYMS. + +config GENKSYMS + bool "genksyms (from source code)" + help + Calculate symbol versions from pre-processed source code using + genksyms. + + If unsure, say Y. + config GENDWARFKSYMS bool "gendwarfksyms (from debugging information)" depends on DEBUG_INFO @@ -176,6 +192,12 @@ config GENDWARFKSYMS depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT # Requires ELF object files. depends on !LTO + help + Calculate symbol versions from DWARF debugging information using + gendwarfksyms. Requires DEBUG_INFO to be enabled. + + If unsure, say N. +endchoice config ASM_MODVERSIONS bool diff --git a/scripts/Makefile b/scripts/Makefile index d7fec46d38c0..8533f4498885 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -53,7 +53,7 @@ hostprogs += unifdef 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.build b/scripts/Makefile.build index c16e4cf54d77..81d9dacad03c 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -107,13 +107,24 @@ 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 @@ -286,14 +297,26 @@ $(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 $@ $< -- cgit v1.2.3 From fc7d5e3210ae083a29ce224ffce18eaf3d1c645a Mon Sep 17 00:00:00 2001 From: Matthew Maurer <mmaurer@google.com> Date: Fri, 3 Jan 2025 17:37:02 +0000 Subject: modpost: Produce extended MODVERSIONS information Generate both the existing modversions format and the new extended one when running modpost. Presence of this metadata in the final .ko is guarded by CONFIG_EXTENDED_MODVERSIONS. We no longer generate an error on long symbols in modpost if CONFIG_EXTENDED_MODVERSIONS is set, as they can now be appropriately encoded in the extended section. These symbols will be skipped in the previous encoding. An error will still be generated if CONFIG_EXTENDED_MODVERSIONS is not set. Reviewed-by: Sami Tolvanen <samitolvanen@google.com> Signed-off-by: Matthew Maurer <mmaurer@google.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- kernel/module/Kconfig | 10 ++++++++ scripts/Makefile.modpost | 1 + scripts/mod/modpost.c | 62 ++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 69 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index d443fc504ffc..9568b629a03c 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -207,6 +207,16 @@ config ASM_MODVERSIONS assembly. This can be enabled only when the target architecture supports it. +config EXTENDED_MODVERSIONS + bool "Extended Module Versioning Support" + depends on MODVERSIONS + help + This enables extended MODVERSIONs support, allowing long symbol + names to be versioned. + + The most likely reason you would enable this is to enable Rust + support. If unsure, say N. + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index ab0e94ea6249..40426fc63509 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,7 @@ MODPOST = $(objtree)/scripts/mod/modpost modpost-args = \ $(if $(CONFIG_MODULES),-M) \ $(if $(CONFIG_MODVERSIONS),-m) \ + $(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/mod/modpost.c b/scripts/mod/modpost.c index dc907014108b..38ff3dd4a9a1 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -33,6 +33,8 @@ static bool module_enabled; static bool modversions; /* Is CONFIG_MODULE_SRCVERSION_ALL set? */ static bool all_versions; +/* 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 */ @@ -1805,6 +1807,49 @@ 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 **/ @@ -1828,9 +1873,14 @@ 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{ 0x%08x, \"%s\" },\n", s->crc, s->name); @@ -1961,6 +2011,7 @@ 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 +2177,7 @@ 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:x")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2175,6 +2226,9 @@ int main(int argc, char **argv) case 'd': missing_namespace_deps = optarg; break; + case 'x': + extended_modversions = true; + break; default: exit(1); } -- cgit v1.2.3 From a937f384c9da493e526ad896ef4e8054526d2941 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra <peterz@infradead.org> Date: Mon, 6 Jan 2025 11:26:48 +0100 Subject: cleanup, tags: Create tags for the cleanup primitives Oleg reported that it is hard to find the definition of things like: __free(argv) without having to do 'git grep "DEFINE_FREE(argv,"'. Add tag generation for the various macros in cleanup.h. Notably 'DEFINE_FREE(argv, ...)' will now generate a 'cleanup_argv' tag, while all the others, eg. 'DEFINE_GUARD(mutex, ...)' will generate 'class_mutex' like tags. Reported-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20250106102647.GB20870@noisy.programming.kicks-ass.net --- scripts/tags.sh | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'scripts') diff --git a/scripts/tags.sh b/scripts/tags.sh index b21236377998..7939aea731f1 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -212,6 +212,13 @@ 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/' -- cgit v1.2.3 From e8639b7ef0f871753b4262ec0eacd3da29eebcee Mon Sep 17 00:00:00 2001 From: Matthew Maurer <mmaurer@google.com> Date: Fri, 3 Jan 2025 17:37:03 +0000 Subject: modpost: Allow extended modversions without basic MODVERSIONS If you know that your kernel modules will only ever be loaded by a newer kernel, you can disable BASIC_MODVERSIONS to save space. This also allows easy creation of test modules to see how tooling will respond to modules that only have the new format. Signed-off-by: Matthew Maurer <mmaurer@google.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- kernel/module/Kconfig | 15 +++++++++++++++ scripts/Makefile.modpost | 1 + scripts/mod/modpost.c | 9 +++++++-- 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 9568b629a03c..4538f3af63e1 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -217,6 +217,21 @@ config EXTENDED_MODVERSIONS The most likely reason you would enable this is to enable Rust support. If unsure, say N. +config BASIC_MODVERSIONS + bool "Basic Module Versioning Support" + depends on MODVERSIONS + default y + help + This enables basic MODVERSIONS support, allowing older tools or + kernels to potentially load modules. + + Disabling this may cause older `modprobe` or `kmod` to be unable + to read MODVERSIONS information from built modules. With this + disabled, older kernels may treat this module as unversioned. + + This is enabled by default when MODVERSIONS are enabled. + If unsure, say Y. + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 40426fc63509..d7d45067d08b 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,7 @@ 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) \ diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 38ff3dd4a9a1..e18ae7dc8140 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -33,6 +33,8 @@ 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 */ @@ -1857,7 +1859,7 @@ static void add_versions(struct buffer *b, struct module *mod) { struct symbol *s; - if (!modversions) + if (!basic_modversions) return; buf_printf(b, "\n"); @@ -2177,7 +2179,7 @@ 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:x")) != -1) { + while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:xb")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2226,6 +2228,9 @@ 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; -- cgit v1.2.3 From 2bff77c665edd854a09c479effe75b3b0e3fedef Mon Sep 17 00:00:00 2001 From: Luca Ceresoli <luca.ceresoli@bootlin.com> Date: Mon, 30 Dec 2024 22:55:10 +0100 Subject: scripts/decode_stacktrace.sh: fix decoding of lines with an additional info Since commit bdf8eafbf7f5 ("arm64: stacktrace: report source of unwind data") a stack trace line can contain an additional info field that was not present before, in the form of one or more letters in parentheses. E.g.: [ 504.517915] led_sysfs_enable+0x54/0x80 (P) ^^^ When this is present, decode_stacktrace decodes the line incorrectly: [ 504.517915] led_sysfs_enable+0x54/0x80 P Extend parsing to decode it correctly: [ 504.517915] led_sysfs_enable (drivers/leds/led-core.c:455 (discriminator 7)) (P) The regex to match such lines assumes the info can be extended in the future to other uppercase characters, and will need to be extended in case other characters will be used. Using a much more generic regex might incur in false positives, so this looked like a good tradeoff. Link: https://lkml.kernel.org/r/20241230-decode_stacktrace-fix-info-v1-1-984910659173@bootlin.com Fixes: bdf8eafbf7f5 ("arm64: stacktrace: report source of unwind data") Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Mark Brown <broonie@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Puranjay Mohan <puranjay@kernel.org> Cc: Thomas Petazzoni <thomas.petazzoni@bootlin.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/decode_stacktrace.sh | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 46fa18b80fc1..17abc4e7a985 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -286,6 +286,18 @@ handle_line() { last=$(( $last - 1 )) fi + # Extract info after the symbol if present. E.g.: + # func_name+0x54/0x80 (P) + # ^^^ + # The regex assumes only uppercase letters will be used. To be + # extended if needed. + local info_str="" + if [[ ${words[$last]} =~ \([A-Z]*\) ]]; then + info_str=${words[$last]} + unset words[$last] + last=$(( $last - 1 )) + fi + if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} # some traces format is "(%pS)", which like "(foo+0x0/0x1 [bar])" @@ -313,9 +325,9 @@ handle_line() { # Add up the line number to the symbol if [[ -z ${module} ]] then - echo "${words[@]}" "$symbol" + echo "${words[@]}" "$symbol ${info_str}" else - echo "${words[@]}" "$symbol $module" + echo "${words[@]}" "$symbol $module ${info_str}" fi } -- cgit v1.2.3 From 4093676f8358be23ee5536b8a32dda381862a3cb Mon Sep 17 00:00:00 2001 From: Colin Ian King <colin.i.king@gmail.com> Date: Wed, 13 Nov 2024 10:21:06 +0000 Subject: scripts/spelling.txt: add more spellings to spelling.txt Add some of the more common spelling mistakes and typos that I've found while fixing up spelling mistakes in the kernel over the past year. Link: https://lkml.kernel.org/r/20241113102106.1163050-1-colin.i.king@gmail.com Signed-off-by: Colin Ian King <colin.i.king@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/spelling.txt | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'scripts') diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 05bd9ca1fbfa..2decc50f5a6e 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 @@ -723,10 +732,12 @@ 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 +778,7 @@ grahpical||graphical granularty||granularity grapic||graphic grranted||granted +grups||groups guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -780,6 +792,7 @@ hardare||hardware harware||hardware hardward||hardware havind||having +heigth||height heirarchically||hierarchically heirarchy||hierarchy heirachy||hierarchy @@ -788,9 +801,11 @@ 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 +857,7 @@ independed||independent indiate||indicate indicat||indicate inexpect||inexpected +infalte||inflate inferface||interface infinit||infinite infomation||information @@ -861,6 +877,7 @@ initators||initiators initialiazation||initialization initializationg||initialization initializiation||initialization +initializtion||initialization initialze||initialize initialzed||initialized initialzing||initializing @@ -877,6 +894,7 @@ instanciate||instantiate instanciated||instantiated instuments||instruments insufficent||insufficient +intead||instead inteface||interface integreated||integrated integrety||integrity @@ -1081,6 +1099,7 @@ notications||notifications notifcations||notifications notifed||notified notity||notify +notfify||notify nubmer||number numebr||number numer||number @@ -1122,6 +1141,7 @@ orientatied||orientated orientied||oriented orignal||original originial||original +orphanded||orphaned otherise||otherwise ouput||output oustanding||outstanding @@ -1184,9 +1204,11 @@ peroid||period persistance||persistence persistant||persistent phoneticly||phonetically +pipline||pipeline plaform||platform plalform||platform platfoem||platform +platfomr||platform platfrom||platform plattform||platform pleaes||please @@ -1211,6 +1233,7 @@ preceeding||preceding preceed||precede precendence||precedence precission||precision +predicition||prediction preemptable||preemptible prefered||preferred prefferably||preferably @@ -1289,6 +1312,7 @@ querrying||querying queus||queues randomally||randomly raoming||roaming +readyness||readiness reasearcher||researcher reasearchers||researchers reasearch||research @@ -1305,8 +1329,10 @@ recieves||receives recieving||receiving recogniced||recognised recognizeable||recognizable +recompte||recompute recommanded||recommended recyle||recycle +redect||reject redircet||redirect redirectrion||redirection redundacy||redundancy @@ -1314,6 +1340,7 @@ reename||rename refcounf||refcount refence||reference refered||referred +referencce||reference referenace||reference refererence||reference refering||referring @@ -1348,11 +1375,13 @@ 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 +1469,7 @@ sequencial||sequential serivce||service serveral||several servive||service +sesion||session setts||sets settting||setting shapshot||snapshot @@ -1602,11 +1632,13 @@ 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 +1665,7 @@ trasfer||transfer trasmission||transmission trasmitter||transmitter treshold||threshold +trigged||triggered triggerd||triggered trigerred||triggered trigerring||triggering @@ -1648,6 +1681,7 @@ uknown||unknown usccess||success uncommited||uncommitted uncompatible||incompatible +uncomressed||uncompressed unconditionaly||unconditionally undeflow||underflow undelying||underlying @@ -1715,6 +1749,7 @@ utitity||utility utitlty||utility vaid||valid vaild||valid +validationg||validating valide||valid variantions||variations varible||variable @@ -1724,6 +1759,7 @@ verbse||verbose veify||verify verfication||verification veriosn||version +versoin||version verisons||versions verison||version veritical||vertical -- cgit v1.2.3 From 10d2711105bd0da774f57bdcd272021b8c453bd3 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven <geert+renesas@glider.be> Date: Thu, 5 Dec 2024 14:20:42 +0100 Subject: checkpatch: update reference to include/asm-<arch> Patch series "Update reference to include/asm-<arch>". Despite "include/asm-<arch>" having been replaced by "arch/<arch>/include/asm" 15 years ago, there are still several references left. This patch series updates the most visible ones. This patch (of 3): "include/asm-<arch>" was replaced by "arch/<arch>/include/asm" a long time ago. Link: https://lkml.kernel.org/r/cover.1733404444.git.geert+renesas@glider.be Link: https://lkml.kernel.org/r/2c4a75726a976d117055055b68a31c40dcab044e.1733404444.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Andy Whitcroft <apw@canonical.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dwaipayan Ray <dwaipayanray1@gmail.com> Cc: Joe Perches <joe@perches.com> Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Nathan Chancellor <nathan@kernel.org> Cc: Nicolas Schier <nicolas@fjasle.eu> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Yury Norov <yury.norov@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/checkpatch.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9eed3683ad76..dbb9c3c6fe30 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2875,7 +2875,7 @@ 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; } -- cgit v1.2.3 From 3735c5225b97cb57745afd151904d08847b09cc7 Mon Sep 17 00:00:00 2001 From: Tamir Duberstein <tamird@gmail.com> Date: Wed, 4 Dec 2024 13:41:06 -0500 Subject: checkpatch: check return of `git_commit_info` Avoid string concatenation with an undefined variable when a reference to a missing commit is contained in a `Fixes` tag. Given this patch: : From: Tamir Duberstein <tamird@gmail.com> : Subject: Test patch : Date: Fri, 25 Oct 2024 19:30:51 -0400 : : This is a test patch. : : Fixes: deadbeef111 : Signed-off-by: Tamir Duberstein <tamird@gmail.com> : --- /dev/null : +++ b/new-file : @@ -0,0 +1 @@ : +Test. Before: WARNING: Please use correct Fixes: style 'Fixes: <12 chars of sha1> ("<title line>")' - ie: 'Fixes: ("commit title")' WARNING: Unknown commit id 'deadbeef111', maybe rebased or not pulled? Use of uninitialized value $cid in concatenation (.) or string at scripts/checkpatch.pl line 3242. After: WARNING: Unknown commit id 'deadbeef111', maybe rebased or not pulled? This patch also reduce duplication slightly. [akpm@linux-foundation.org: s/12 chars of sha1/12+ chars of sha1/, per Jon] Link: https://lkml.kernel.org/r/87o70kt232.fsf@trenco.lwn.net Link: https://lkml.kernel.org/r/20241204-checkpatch-missing-commit-v1-1-68b34c94944e@gmail.com Signed-off-by: Tamir Duberstein <tamird@gmail.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Dwaipayan Ray <dwaipayanray1@gmail.com> Cc: Joe Perches <joe@perches.com> Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/checkpatch.pl | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index dbb9c3c6fe30..2bdc3d169af5 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3237,12 +3237,12 @@ sub process { my ($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; } } } -- cgit v1.2.3 From 551dbd1ec7ff10e06ec077eb264cec0c971b66eb Mon Sep 17 00:00:00 2001 From: Easwar Hariharan <eahariha@linux.microsoft.com> Date: Tue, 10 Dec 2024 22:02:33 +0000 Subject: coccinelle: misc: add secs_to_jiffies script MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This script finds and suggests conversions of timeout patterns that result in seconds-denominated timeouts to use the new secs_to_jiffies() API in include/linux/jiffies.h for better readability. Link: https://lkml.kernel.org/r/20241210-converge-secs-to-jiffies-v3-2-ddfefd7e9f2a@linux.microsoft.com Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com> Suggested-by: Anna-Maria Behnsen <anna-maria@linutronix.de> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andrew Lunn <andrew+netdev@lunn.ch> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Daniel Mack <daniel@zonque.org> Cc: David Airlie <airlied@gmail.com> Cc: David S. Miller <davem@davemloft.net> Cc: Dick Kennedy <dick.kennedy@broadcom.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Florian Fainelli <florian.fainelli@broadcom.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Haojian Zhuang <haojian.zhuang@gmail.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jack Wang <jinpu.wang@cloud.ionos.com> Cc: Jakub Kicinski <kuba@kernel.org> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: James Smart <james.smart@broadcom.com> Cc: Jaroslav Kysela <perex@perex.cz> Cc: Jeff Johnson <jjohnson@kernel.org> Cc: Jeff Johnson <quic_jjohnson@quicinc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jeroen de Borst <jeroendb@google.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: Joe Lawrence <joe.lawrence@redhat.com> Cc: Johan Hedberg <johan.hedberg@gmail.com> Cc: Josh Poimboeuf <jpoimboe@kernel.org> Cc: Jozsef Kadlecsik <kadlec@netfilter.org> Cc: Julia Lawall <julia.lawall@inria.fr> Cc: Kalle Valo <kvalo@kernel.org> Cc: Louis Peens <louis.peens@corigine.com> Cc: Lucas De Marchi <lucas.demarchi@intel.com> Cc: Luiz Augusto von Dentz <luiz.dentz@gmail.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Marcel Holtmann <marcel@holtmann.org> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Maxime Ripard <mripard@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Naveen N Rao <naveen@kernel.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Nicolas Palix <nicolas.palix@imag.fr> Cc: Oded Gabbay <ogabbay@kernel.org> Cc: Ofir Bitton <obitton@habana.ai> Cc: Pablo Neira Ayuso <pablo@netfilter.org> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Praveen Kaligineedi <pkaligineedi@google.com> Cc: Ray Jui <rjui@broadcom.com> Cc: Robert Jarzmik <robert.jarzmik@free.fr> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roger Pau Monné <roger.pau@citrix.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Scott Branden <sbranden@broadcom.com> Cc: Shailend Chand <shailend@google.com> Cc: Simona Vetter <simona@ffwll.ch> Cc: Simon Horman <horms@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Takashi Iwai <tiwai@suse.com> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com> Cc: Thomas Zimmermann <tzimmermann@suse.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Xiubo Li <xiubli@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/coccinelle/misc/secs_to_jiffies.cocci | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 scripts/coccinelle/misc/secs_to_jiffies.cocci (limited to 'scripts') diff --git a/scripts/coccinelle/misc/secs_to_jiffies.cocci b/scripts/coccinelle/misc/secs_to_jiffies.cocci new file mode 100644 index 000000000000..8bbb2884ea5d --- /dev/null +++ b/scripts/coccinelle/misc/secs_to_jiffies.cocci @@ -0,0 +1,22 @@ +// 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) -- cgit v1.2.3 From 93b6bd40688ba17225ba8c5f28e8ccb713359b05 Mon Sep 17 00:00:00 2001 From: Shivam Chaudhary <cvam0000@gmail.com> Date: Wed, 11 Dec 2024 21:19:03 +0530 Subject: kernel-wide: add explicity||explicitly to spelling.txt Correct the spelling dictionary so that future instances will be caught by checkpatch, and fix the instances found. Link: https://lkml.kernel.org/r/20241211154903.47027-1-cvam0000@gmail.com Signed-off-by: Shivam Chaudhary <cvam0000@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Leon Romanovsky <leon@kernel.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naveen N Rao <naveen@kernel.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Shivam Chaudhary <cvam0000@gmail.com> Cc: Colin Ian King <colin.i.king@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- arch/powerpc/kvm/book3s_hv.c | 2 +- drivers/infiniband/hw/hfi1/iowait.h | 2 +- drivers/infiniband/hw/usnic/usnic_abi.h | 2 +- drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c | 2 +- drivers/scsi/cxlflash/superpipe.c | 2 +- scripts/spelling.txt | 1 + tools/testing/selftests/pidfd/pidfd_test.c | 2 +- 7 files changed, 7 insertions(+), 6 deletions(-) (limited to 'scripts') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 25429905ae90..86bff159c51e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4957,7 +4957,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * states are synchronized from L0 to L1. L1 needs to inform L0 about * MER=1 only when there are pending external interrupts. * In the above if check, MER bit is set if there are pending - * external interrupts. Hence, explicity mask off MER bit + * external interrupts. Hence, explicitly mask off MER bit * here as otherwise it may generate spurious interrupts in L2 KVM * causing an endless loop, which results in L2 guest getting hung. */ diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h index 49805a24bb0a..7259f4f55700 100644 --- a/drivers/infiniband/hw/hfi1/iowait.h +++ b/drivers/infiniband/hw/hfi1/iowait.h @@ -92,7 +92,7 @@ struct iowait_work { * * The lock field is used by waiters to record * the seqlock_t that guards the list head. - * Waiters explicity know that, but the destroy + * Waiters explicitly know that, but the destroy * code that unwaits QPs does not. */ struct iowait { diff --git a/drivers/infiniband/hw/usnic/usnic_abi.h b/drivers/infiniband/hw/usnic/usnic_abi.h index 7fe9502ce8d3..86a82a4da0aa 100644 --- a/drivers/infiniband/hw/usnic/usnic_abi.h +++ b/drivers/infiniband/hw/usnic/usnic_abi.h @@ -72,7 +72,7 @@ struct usnic_ib_create_qp_resp { u64 bar_bus_addr; u32 bar_len; /* - * WQ, RQ, CQ are explicity specified bc exposing a generic resources inteface + * WQ, RQ, CQ are explicitly specified bc exposing a generic resources inteface * expands the scope of ABI to many files. */ u32 wq_cnt; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c index 0949e7975ff1..b70d20128f98 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c @@ -1810,7 +1810,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt) rfi->cur_idx = cur_idx; } } else { - /* explicity window move updating the expected index */ + /* explicitly window move updating the expected index */ exp_idx = reorder_data[BRCMF_RXREORDER_EXPIDX_OFFSET]; brcmf_dbg(DATA, "flow-%d (0x%x): change expected: %d -> %d\n", diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c index b375509d1470..97631f48e19d 100644 --- a/drivers/scsi/cxlflash/superpipe.c +++ b/drivers/scsi/cxlflash/superpipe.c @@ -966,7 +966,7 @@ static int cxlflash_disk_detach(struct scsi_device *sdev, void *detach) * * This routine is the release handler for the fops registered with * the CXL services on an initial attach for a context. It is called - * when a close (explicity by the user or as part of a process tear + * when a close (explicitly by the user or as part of a process tear * down) is performed on the adapter file descriptor returned to the * user. The user should be aware that explicitly performing a close * considered catastrophic and subsequent usage of the superpipe API diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 2decc50f5a6e..a290db720b0f 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -678,6 +678,7 @@ exmaple||example expecially||especially experies||expires explicite||explicit +explicity||explicitly explicitely||explicitly explict||explicit explictely||explicitly diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9faa686f90e4..e9728e86b4f2 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -497,7 +497,7 @@ static int child_poll_leader_exit_test(void *args) pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL); /* - * glibc exit calls exit_group syscall, so explicity call exit only + * glibc exit calls exit_group syscall, so explicitly call exit only * so that only the group leader exits, leaving the threads alone. */ *child_exit_secs = time(NULL); -- cgit v1.2.3 From 2217573f4c8797eb5ed764a728f986aa80bd403c Mon Sep 17 00:00:00 2001 From: Costa Shulyupin <costa.shul@redhat.com> Date: Mon, 13 Jan 2025 10:55:47 +0200 Subject: scripts/tags.sh: Don't tag usages of DECLARE_BITMAP For all bitmap declarations like DECLARE_BITMAP(x, y); ctags generates multiple DECLARE_BITMAP tags for each usage because it doesn't expand the DECLARE_BITMAP macro. Configure ctags to skip generating tags for DECLARE_BITMAP in such cases. The #define DECLARE_BITMAP itself and declared bitmaps are tagged correctly. Signed-off-by: Costa Shulyupin <costa.shul@redhat.com> Link: https://lore.kernel.org/r/20250113085554.649141-1-costa.shul@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> --- scripts/tags.sh | 1 + 1 file changed, 1 insertion(+) (limited to 'scripts') diff --git a/scripts/tags.sh b/scripts/tags.sh index 7102f14fc775..dba0bb0213eb 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -261,6 +261,7 @@ exuberant() # identifiers to ignore by ctags local ign=( ACPI_EXPORT_SYMBOL + DECLARE_BITMAP DEFINE_{TRACE,MUTEX,TIMER} EXPORT_SYMBOL EXPORT_SYMBOL_GPL EXPORT_TRACEPOINT_SYMBOL EXPORT_TRACEPOINT_SYMBOL_GPL -- cgit v1.2.3 From 25ff08aa43e373a61c3e36fc7d7cae88ed0fc2d7 Mon Sep 17 00:00:00 2001 From: Torsten Hilbrich <torsten.hilbrich@secunet.com> Date: Mon, 13 Jan 2025 07:01:29 +0100 Subject: kbuild: Fix signing issue for external modules When running the sign script the kernel is within the source directory of external modules. This caused issues when the kernel uses relative paths, like: make[5]: Entering directory '/build/client/devel/kernel/work/linux-2.6' make[6]: Entering directory '/build/client/devel/addmodules/vtx/work/vtx' INSTALL /build/client/devel/addmodules/vtx/_/lib/modules/6.13.0-devel+/extra/vtx.ko SIGN /build/client/devel/addmodules/vtx/_/lib/modules/6.13.0-devel+/extra/vtx.ko /bin/sh: 1: scripts/sign-file: not found DEPMOD /build/client/devel/addmodules/vtx/_/lib/modules/6.13.0-devel+ Working around it by using absolute pathes here. Fixes: 13b25489b6f8 ("kbuild: change working directory to external module directory with M=") Signed-off-by: Torsten Hilbrich <torsten.hilbrich@secunet.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/Makefile.modinst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') 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),) -- cgit v1.2.3 From 015b0bfe754ae157cfccd7a13c41391124b115f2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:39 +0900 Subject: genksyms: rename m_abstract_declarator to abstract_declarator This is called "abstract-declarator" in K&R. [1] I am not sure what "m_" stands for, but the name is clear enough without it. No functional changes are intended. [1] https://cs.wmich.edu/~gupta/teaching/cs4850/sumII06/The%20syntax%20of%20C%20in%20Backus-Naur%20form.htm Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 689cb6bb40b6..02f2f713ec5a 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -367,17 +367,17 @@ parameter_declaration_list: ; parameter_declaration: - decl_specifier_seq m_abstract_declarator + decl_specifier_seq abstract_declarator { $$ = $2 ? $2 : $1; } ; -m_abstract_declarator: - ptr_operator m_abstract_declarator +abstract_declarator: + ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } - | direct_m_abstract_declarator + | direct_abstract_declarator ; -direct_m_abstract_declarator: +direct_abstract_declarator: /* empty */ { $$ = NULL; } | IDENT { /* For version 2 checksums, we don't want to remember @@ -391,13 +391,13 @@ direct_m_abstract_declarator: { remove_node($1); $$ = $1; } - | direct_m_abstract_declarator '(' parameter_declaration_clause ')' + | direct_abstract_declarator '(' parameter_declaration_clause ')' { $$ = $4; } - | direct_m_abstract_declarator '(' error ')' + | direct_abstract_declarator '(' error ')' { $$ = $4; } - | direct_m_abstract_declarator BRACKET_PHRASE + | direct_abstract_declarator BRACKET_PHRASE { $$ = $2; } - | '(' m_abstract_declarator ')' + | '(' abstract_declarator ')' { $$ = $3; } | '(' error ')' { $$ = $3; } -- cgit v1.2.3 From f33bfbd171a03c5d3f64ce956ccdfbece7114da4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:40 +0900 Subject: genksyms: rename cvar_qualifier to type_qualifier I believe "cvar" stands for "Const, Volatile, Attribute, or Restrict". This is called "type-qualifier" in K&R. [1] Adopt this more generic naming. No functional changes are intended. [1] https://cs.wmich.edu/~gupta/teaching/cs4850/sumII06/The%20syntax%20of%20C%20in%20Backus-Naur%20form.htm Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 02f2f713ec5a..8f62b9f0d99c 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -223,7 +223,7 @@ storage_class_specifier: type_specifier: simple_type_specifier - | cvar_qualifier + | type_qualifier | TYPEOF_KEYW '(' parameter_declaration ')' | TYPEOF_PHRASE @@ -270,21 +270,21 @@ simple_type_specifier: ; ptr_operator: - '*' cvar_qualifier_seq_opt + '*' type_qualifier_seq_opt { $$ = $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 + | type_qualifier_seq type_qualifier { $$ = $2; } ; -cvar_qualifier: +type_qualifier: CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ -- cgit v1.2.3 From bc3a812b751ae1a4d91b3ea667ed77e76398bf46 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:41 +0900 Subject: genksyms: reduce type_qualifier directly to decl_specifier A type_qualifier (const, volatile, etc.) is not a type_specifier. According to K&R [1], a type-qualifier should be directly reduced to a declaration-specifier. <declaration-specifier> ::= <storage-class-specifier> | <type-specifier> | <type-qualifier> [1]: https://cs.wmich.edu/~gupta/teaching/cs4850/sumII06/The%20syntax%20of%20C%20in%20Backus-Naur%20form.htm Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 8f62b9f0d99c..20cb3db7f149 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -211,6 +211,7 @@ decl_specifier: $$ = $1; } | type_specifier + | type_qualifier ; storage_class_specifier: @@ -223,7 +224,6 @@ storage_class_specifier: type_specifier: simple_type_specifier - | type_qualifier | TYPEOF_KEYW '(' parameter_declaration ')' | TYPEOF_PHRASE -- cgit v1.2.3 From 3ccda63a3af5f12c9e0b01c06561285227d2f79c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:42 +0900 Subject: genksyms: fix 6 shift/reduce conflicts and 5 reduce/reduce conflicts The genksyms parser has ambiguities in its grammar, which are currently suppressed by a workaround in scripts/genksyms/Makefile. Building genksyms with W=1 generates the following warnings: YACC scripts/genksyms/parse.tab.[ch] scripts/genksyms/parse.y: warning: 9 shift/reduce conflicts [-Wconflicts-sr] scripts/genksyms/parse.y: warning: 5 reduce/reduce conflicts [-Wconflicts-rr] scripts/genksyms/parse.y: note: rerun with option '-Wcounterexamples' to generate conflict counterexamples The comment in the parser describes the current problem: /* This wasn't really a typedef name but an identifier that shadows one. */ Consider the following simple C code: typedef int foo; void my_func(foo foo) {} In the function parameter list (foo foo), the first 'foo' is a type specifier (typedef'ed as 'int'), while the second 'foo' is an identifier. However, the lexer cannot distinguish between the two. Since 'foo' is already typedef'ed, the lexer returns TYPE for both instances, instead of returning IDENT for the second one. To support shadowed identifiers, TYPE can be reduced to either a simple_type_specifier or a direct_abstract_declarator, which creates a grammatical ambiguity. Without analyzing the grammar context, it is very difficult to resolve this correctly. This commit introduces a flag, dont_want_type_specifier, which allows the parser to inform the lexer whether an identifier is expected. When dont_want_type_specifier is true, the type lookup is suppressed, and the lexer returns IDENT regardless of any preceding typedef. After this commit, only 3 shift/reduce conflicts will remain. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/genksyms.h | 3 +++ scripts/genksyms/lex.l | 9 ++++++++- scripts/genksyms/parse.y | 37 +++++++++++++++---------------------- 3 files changed, 26 insertions(+), 23 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 8c45ada59ece..0c355075f0e6 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -12,6 +12,7 @@ #ifndef MODUTILS_GENKSYMS_H #define MODUTILS_GENKSYMS_H 1 +#include <stdbool.h> #include <stdio.h> #include <list_types.h> @@ -66,6 +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/lex.l b/scripts/genksyms/lex.l index a4d7495eaf75..e886133af578 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> @@ -113,6 +114,12 @@ 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) { @@ -207,7 +214,7 @@ repeat: goto repeat; } } - if (!suppress_type_lookup) + if (!suppress_type_lookup && !dont_want_type_specifier) { if (find_symbol(yytext, SYM_TYPEDEF, 1)) token = TYPE; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 20cb3db7f149..dc575d467bbf 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" @@ -148,6 +149,7 @@ simple_declaration: current_name = NULL; } $$ = $3; + dont_want_type_specifier = false; } ; @@ -169,6 +171,7 @@ init_declarator_list: is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; $$ = $1; + dont_want_type_specifier = true; } | init_declarator_list ',' init_declarator { struct string_list *decl = *$3; @@ -184,6 +187,7 @@ init_declarator_list: is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; $$ = $3; + dont_want_type_specifier = true; } ; @@ -210,7 +214,7 @@ decl_specifier: remove_node($1); $$ = $1; } - | type_specifier + | type_specifier { dont_want_type_specifier = true; $$ = $1; } | type_qualifier ; @@ -307,15 +311,7 @@ direct_declarator: current_name = (*$1)->string; $$ = $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; } @@ -335,8 +331,7 @@ nested_declarator: ; direct_nested_declarator: - IDENT - | TYPE + IDENT { $$ = $1; dont_want_type_specifier = false; } | direct_nested_declarator '(' parameter_declaration_clause ')' { $$ = $4; } | direct_nested_declarator '(' error ')' @@ -362,8 +357,9 @@ parameter_declaration_list_opt: parameter_declaration_list: parameter_declaration + { $$ = $1; dont_want_type_specifier = false; } | parameter_declaration_list ',' parameter_declaration - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } ; parameter_declaration: @@ -375,6 +371,7 @@ abstract_declarator: ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } | direct_abstract_declarator + { $$ = $1; dont_want_type_specifier = false; } ; direct_abstract_declarator: @@ -385,12 +382,6 @@ direct_abstract_declarator: remove_node($1); $$ = $1; } - /* This wasn't really a typedef name but an identifier that - shadows one. */ - | TYPE - { remove_node($1); - $$ = $1; - } | direct_abstract_declarator '(' parameter_declaration_clause ')' { $$ = $4; } | direct_abstract_declarator '(' error ')' @@ -440,9 +431,9 @@ 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: @@ -452,7 +443,9 @@ 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: -- cgit v1.2.3 From 668de2b9d48dccdc1b992e07287f15459515fefb Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:43 +0900 Subject: genksyms: fix last 3 shift/reduce conflicts The genksyms parser has ambiguities in its grammar, which are currently suppressed by a workaround in scripts/genksyms/Makefile. Building genksyms with W=1 generates the following warnings: YACC scripts/genksyms/parse.tab.[ch] scripts/genksyms/parse.y: warning: 3 shift/reduce conflicts [-Wconflicts-sr] scripts/genksyms/parse.y: note: rerun with option '-Wcounterexamples' to generate conflict counterexamples The ambiguity arises when decl_specifier_seq is followed by '(' because the following two interpretations are possible: - decl_specifier_seq direct_abstract_declarator '(' parameter_declaration_clause ')' - decl_specifier_seq '(' abstract_declarator ')' This issue occurs because the current parser allows an empty string to be reduced to direct_abstract_declarator, which is incorrect. K&R [1] explains the correct grammar: <parameter-declaration> ::= {<declaration-specifier>}+ <declarator> | {<declaration-specifier>}+ <abstract-declarator> | {<declaration-specifier>}+ <abstract-declarator> ::= <pointer> | <pointer> <direct-abstract-declarator> | <direct-abstract-declarator> <direct-abstract-declarator> ::= ( <abstract-declarator> ) | {<direct-abstract-declarator>}? [ {<constant-expression>}? ] | {<direct-abstract-declarator>}? ( {<parameter-type-list>}? ) This commit resolves all remaining conflicts. We need to consider the difference between the following two examples: [Example 1] ( <abstract-declarator> ) can become <direct-abstract-declarator> void my_func(int (foo)); ... is equivalent to: void my_func(int foo); [Example 2] ( <parameter-type-list> ) can become <direct-abstract-declarator> typedef int foo; void my_func(int (foo)); ... is equivalent to: void my_func(int (*callback)(int)); Please note that the function declaration is identical in both examples, but the preceding typedef creates the distinction. I introduced a new term, open_paren, to enable the type lookup immediately after the '(' token. Without this, we cannot distinguish between [Example 1] and [Example 2]. [1]: https://cs.wmich.edu/~gupta/teaching/cs4850/sumII06/The%20syntax%20of%20C%20in%20Backus-Naur%20form.htm Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index dc575d467bbf..fafce939c32f 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -363,35 +363,47 @@ parameter_declaration_list: ; parameter_declaration: - decl_specifier_seq abstract_declarator + decl_specifier_seq abstract_declarator_opt { $$ = $2 ? $2 : $1; } ; +abstract_declarator_opt: + /* empty */ { $$ = NULL; } + | abstract_declarator + ; + abstract_declarator: - ptr_operator abstract_declarator + ptr_operator + | ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } | direct_abstract_declarator { $$ = $1; dont_want_type_specifier = false; } ; direct_abstract_declarator: - /* empty */ { $$ = NULL; } - | IDENT + IDENT { /* For version 2 checksums, we don't want to remember private parameter names. */ remove_node($1); $$ = $1; } - | direct_abstract_declarator '(' parameter_declaration_clause ')' + | direct_abstract_declarator open_paren parameter_declaration_clause ')' { $$ = $4; } - | direct_abstract_declarator '(' error ')' + | direct_abstract_declarator open_paren error ')' { $$ = $4; } | direct_abstract_declarator BRACKET_PHRASE { $$ = $2; } - | '(' abstract_declarator ')' + | open_paren parameter_declaration_clause ')' { $$ = $3; } - | '(' error ')' + | open_paren abstract_declarator ')' { $$ = $3; } + | open_paren error ')' + { $$ = $3; } + | BRACKET_PHRASE + ; + +open_paren: + '(' { $$ = $1; dont_want_type_specifier = false; } ; function_definition: -- cgit v1.2.3 From a95298656c434357b38bec242412c65dcf6114d1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:44 +0900 Subject: genksyms: remove Makefile hack This workaround was introduced for suppressing the reduce/reduce conflict warnings because the %expect-rr directive, which is applicable only to GLR parsers, cannot be used for genksyms. Since there are no longer any conflicts, this Makefile hack is now unnecessary. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/Makefile | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index 312edccda736..4350311fb7b3 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -4,24 +4,6 @@ hostprogs-always-y += genksyms genksyms-objs := genksyms.o parse.tab.o lex.lex.o -# FIXME: fix the ambiguous grammar in parse.y and delete this hack -# -# Suppress shift/reduce, reduce/reduce conflicts warnings -# unless W=1 is specified. -# -# Just in case, run "$(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) -- cgit v1.2.3 From c2f1846ba87ead7ac544be624c13249d6b90eca0 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:45 +0900 Subject: genksyms: restrict direct-abstract-declarator to take one parameter-type-list While there is no more grammatical ambiguity in genksyms, the parser logic is still inaccurate. For example, genksyms accepts the following invalid C code: void my_func(int ()(int)); This should result in a syntax error because () cannot be reduced to <direct-abstract-declarator>. ( <abstract-declarator> ) can be reduced, but <abstract-declarator> must not be empty in the following grammar from K&R [1]: <direct-abstract-declarator> ::= ( <abstract-declarator> ) | {<direct-abstract-declarator>}? [ {<constant-expression>}? ] | {<direct-abstract-declarator>}? ( {<parameter-type-list>}? ) Furthermore, genksyms accepts the following weird code: void my_func(int (*callback)(int)(int)(int)); The parser allows <direct-abstract-declarator> to recursively absorb multiple ( {<parameter-type-list>}? ), but this behavior is incorrect. In the example above, (*callback) should be followed by at most one (int). [1]: https://cs.wmich.edu/~gupta/teaching/cs4850/sumII06/The%20syntax%20of%20C%20in%20Backus-Naur%20form.htm Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index fafce939c32f..03cdd8d53c13 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -381,20 +381,24 @@ abstract_declarator: ; 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); $$ = $1; } - | direct_abstract_declarator open_paren parameter_declaration_clause ')' - { $$ = $4; } - | direct_abstract_declarator open_paren error ')' + | direct_abstract_declarator1 open_paren error ')' { $$ = $4; } - | direct_abstract_declarator BRACKET_PHRASE + | direct_abstract_declarator1 BRACKET_PHRASE { $$ = $2; } - | open_paren parameter_declaration_clause ')' - { $$ = $3; } | open_paren abstract_declarator ')' { $$ = $3; } | open_paren error ')' -- cgit v1.2.3 From aa710cee0d677043f49a447c4665df51a553a2ba Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:46 +0900 Subject: genksyms: restrict direct-declarator to take one parameter-type-list Similar to the previous commit, this change makes the parser logic a little more accurate. Currently, genksyms accepts the following invalid code: struct foo { int (*callback)(int)(int)(int); }; A direct-declarator should not recursively absorb multiple ( parameter-type-list ) constructs. In the example above, (*callback) should be followed by at most one (int). Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 03cdd8d53c13..33a6aab53b69 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -331,12 +331,16 @@ nested_declarator: ; direct_nested_declarator: - IDENT { $$ = $1; dont_want_type_specifier = false; } - | direct_nested_declarator '(' parameter_declaration_clause ')' + direct_nested_declarator1 + | direct_nested_declarator1 '(' parameter_declaration_clause ')' { $$ = $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; } -- cgit v1.2.3 From ccc11a195c69b0c01ee140aecadfbdcdcdd03605 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:47 +0900 Subject: genksyms: record attributes consistently for init-declarator I believe the missing action here is a bug. For rules with no explicit action, the following default is used: { $$ = $1; } However, in this case, $1 is the value of attribute_opt itself. As a result, the value of attribute_opt is always NULL. The following test code demonstrates inconsistent behavior. int x __attribute__((__aligned__(4))); int y __attribute__((__aligned__(4))) = 0; The attribute is recorded only when followed by an initializer. This commit adds the correct action to propagate the value of the ATTRIBUTE_PHRASE token. With this change, the attribute in the example above is consistently recorded for both 'x' and 'y'. [Before] $ cat <<EOF | scripts/genksyms/genksyms -d int x __attribute__((__aligned__(4))); int y __attribute__((__aligned__(4))) = 0; EOF Defn for type0 x == <int x > Defn for type0 y == <int y __attribute__ ( ( __aligned__ ( 4 ) ) ) > Hash table occupancy 2/4096 = 0.000488281 [After] $ cat <<EOF | scripts/genksyms/genksyms -d int x __attribute__((__aligned__(4))); int y __attribute__((__aligned__(4))) = 0; EOF Defn for type0 x == <int x __attribute__ ( ( __aligned__ ( 4 ) ) ) > Defn for type0 y == <int y __attribute__ ( ( __aligned__ ( 4 ) ) ) > Hash table occupancy 2/4096 = 0.000488281 Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 33a6aab53b69..e3c160046143 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -480,7 +480,7 @@ member_bitfield_declarator: attribute_opt: /* empty */ { $$ = NULL; } - | attribute_opt ATTRIBUTE_PHRASE + | attribute_opt ATTRIBUTE_PHRASE { $$ = $2; } ; enum_body: -- cgit v1.2.3 From ec28bfff83c49b65527f0055e313d9d7c8c04a31 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:48 +0900 Subject: genksyms: decouple ATTRIBUTE_PHRASE from type-qualifier The __attribute__ keyword can appear in more contexts than 'const' or 'volatile'. To avoid grammatical conflicts with future changes, ATTRIBUTE_PHRASE should not be reduced into type_qualifier. No functional changes are intended. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index e3c160046143..cd933a95548d 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -216,6 +216,7 @@ decl_specifier: } | type_specifier { dont_want_type_specifier = true; $$ = $1; } | type_qualifier + | ATTRIBUTE_PHRASE ; storage_class_specifier: @@ -285,11 +286,13 @@ type_qualifier_seq_opt: type_qualifier_seq: type_qualifier + | ATTRIBUTE_PHRASE | type_qualifier_seq type_qualifier { $$ = $2; } + | type_qualifier_seq ATTRIBUTE_PHRASE { $$ = $2; } ; type_qualifier: - CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE + CONST_KEYW | VOLATILE_KEYW | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ remove_node($1); -- cgit v1.2.3 From 2966b66c94a2b0d897f8626b8f2c50a0fd4878a9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:49 +0900 Subject: genksyms: fix syntax error for attribute before abstract_declarator A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, with CONFIG_MODVERSIONS=y on v6.13-rc1: $ make -s KCFLAGS=-D__GENKSYMS__ init/main.i $ cat init/main.i | scripts/genksyms/genksyms -w [ snip ] ./include/linux/efi.h:1225: syntax error The syntax error occurs in the following code in include/linux/efi.h: efi_status_t efi_call_acpi_prm_handler(efi_status_t (__efiapi *handler_addr)(u64, void *), u64 param_buffer_addr, void *context); The issue arises from __efiapi, which is defined as either __attribute__((ms_abi)) or __attribute__((regparm(0))). This commit allows abstract_declarator to be prefixed with attributes. To avoid conflicts, I tweaked the rule for decl_specifier_seq. Due to this change, a standalone attribute cannot become decl_specifier_seq. Otherwise, I do not know how to resolve the conflicts. The following code, which was previously accepted by genksyms, will now result in a syntax error: void my_func(__attribute__((unused))x); I do not think it is a big deal because GCC also fails to parse it. $ echo 'void my_func(__attribute__((unused))x);' | gcc -c -x c - <stdin>:1:37: error: unknown type name 'x' Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index cd933a95548d..54e16c2e0b4b 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -203,8 +203,9 @@ 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: @@ -216,7 +217,6 @@ decl_specifier: } | type_specifier { dont_want_type_specifier = true; $$ = $1; } | type_qualifier - | ATTRIBUTE_PHRASE ; storage_class_specifier: @@ -406,8 +406,8 @@ direct_abstract_declarator1: { $$ = $4; } | direct_abstract_declarator1 BRACKET_PHRASE { $$ = $2; } - | open_paren abstract_declarator ')' - { $$ = $3; } + | open_paren attribute_opt abstract_declarator ')' + { $$ = $4; } | open_paren error ')' { $$ = $3; } | BRACKET_PHRASE -- cgit v1.2.3 From a8b7d066f8626ec847d3e66aef1320968d1fe298 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:50 +0900 Subject: genksyms: fix syntax error for attribute before nested_declarator A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, with CONFIG_MODVERSIONS=y on v6.13-rc1: $ make -s KCFLAGS=-D__GENKSYMS__ drivers/acpi/prmt.i $ cat drivers/acpi/prmt.i | scripts/genksyms/genksyms -w [ snip ] drivers/acpi/prmt.c:56: syntax error The syntax error occurs in the following code in drivers/acpi/prmt.c: struct prm_handler_info { [ snip ] efi_status_t (__efiapi *handler_addr)(u64, void *); [ snip ] }; The issue arises from __efiapi, which is defined as either __attribute__((ms_abi)) or __attribute__((regparm(0))). This commit allows nested_declarator to be prefixed with attributes. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 54e16c2e0b4b..49d3e536b9a8 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -345,8 +345,8 @@ direct_nested_declarator1: { $$ = $4; } | direct_nested_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' nested_declarator ')' - { $$ = $3; } + | '(' attribute_opt nested_declarator ')' + { $$ = $4; } | '(' error ')' { $$ = $3; } ; -- cgit v1.2.3 From 2ac068cb0b366c61e7aebaccf0240eae8b2c1b43 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:51 +0900 Subject: genksyms: fix syntax error for attribute after abstact_declarator A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, with CONFIG_MODVERSIONS=y on v6.13-rc1: $ make -s KCFLAGS=-D__GENKSYMS__ kernel/module/main.i $ cat kernel/module/main.i | scripts/genksyms/genksyms -w [ snip ] kernel/module/main.c:97: syntax error The syntax error occurs in the following code in kernel/module/main.c: static void __mod_update_bounds(enum mod_mem_type type __maybe_unused, void *base, unsigned int size, struct mod_tree_root *tree) { [ snip ] } The issue arises from __maybe_unused, which is defined as __attribute__((__unused__)). This commit allows direct_abstract_declarator to be followed with attributes. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 49d3e536b9a8..82774df50642 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -383,8 +383,8 @@ abstract_declarator: ptr_operator | ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } - | direct_abstract_declarator - { $$ = $1; dont_want_type_specifier = false; } + | direct_abstract_declarator attribute_opt + { $$ = $2; dont_want_type_specifier = false; } ; direct_abstract_declarator: -- cgit v1.2.3 From 82db1c29103ebf581484c0b30805e68726121dcb Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:52 +0900 Subject: genksyms: fix syntax error for attribute after 'struct' A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, with CONFIG_MODVERSIONS=y on v6.13-rc1: $ make -s KCFLAGS=-D__GENKSYMS__ arch/x86/kernel/cpu/mshyperv.i $ cat arch/x86/kernel/cpu/mshyperv.i | scripts/genksyms/genksyms -w [ snip ] ./arch/x86/include/asm/svm.h:122: syntax error The syntax error occurs in the following code in arch/x86/include/asm/svm.h: struct __attribute__ ((__packed__)) vmcb_control_area { [ snip ] }; The issue arises from __attribute__ immediately after the 'struct' keyword. This commit allows the 'struct' keyword to be followed by attributes. The lexer must be adjusted because dont_want_brace_phase should not be decremented while processing attributes. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/lex.l | 7 ++++++- scripts/genksyms/parse.y | 10 +++++----- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index e886133af578..a1f969dcf24f 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -438,7 +438,12 @@ 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 82774df50642..33639232a709 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -234,16 +234,16 @@ type_specifier: /* 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; $$ = $2; } + | STRUCT_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; } | UNION_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; } | ENUM_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; } /* Full definitions of an s/u/e. Record it. */ - | STRUCT_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_STRUCT); $$ = $3; } + | STRUCT_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; } | UNION_KEYW IDENT class_body { record_compound($1, $2, $3, SYM_UNION); $$ = $3; } | ENUM_KEYW IDENT enum_body @@ -254,7 +254,7 @@ type_specifier: | ENUM_KEYW enum_body { add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; } /* Anonymous s/u definitions. Nothing needs doing. */ - | STRUCT_KEYW class_body { $$ = $2; } + | STRUCT_KEYW attribute_opt class_body { $$ = $3; } | UNION_KEYW class_body { $$ = $2; } ; -- cgit v1.2.3 From c6da721f5889b650bc99a77ac3b6dcf86f4cb138 Mon Sep 17 00:00:00 2001 From: David Reaver <me@davidreaver.com> Date: Wed, 8 Jan 2025 11:24:54 -0800 Subject: checkpatch: remove migrated RCU APIs from deprecated_apis The deprecated_apis map was created in [1] so checkpatch would flag deprecated RCU APIs. These deprecated APIs have since been removed from the kernel. This patch removes them from this map so checkpatch doesn't waste time looking for them, and so readers of checkpatch looking for deprecated APIs don't waste time searching for them. Link: https://lore.kernel.org/all/20181111192904.3199-13-paulmck@linux.ibm.com/ [1] Link: https://lkml.kernel.org/r/20250108192456.47871-1-me@davidreaver.com Signed-off-by: David Reaver <me@davidreaver.com> Reviewed-by: Paul E. McKenney <paulmck@kernel.org> Reviewed-by: Kuan-Wei Chiu <visitorckw@gmail.com> Acked-by: Joe Perches <joe@perches.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Dwaipayan Ray <dwaipayanray1@gmail.com> Cc: Krister Johansen <kjlx@templeofstupid.com> Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/checkpatch.pl | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2bdc3d169af5..c625da28cdae 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -834,16 +834,6 @@ 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", -- cgit v1.2.3 From d22feb5b64a4ecb1f029b3266148823c9fe569ee Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter@linaro.org> Date: Fri, 10 Jan 2025 10:12:17 +0300 Subject: checkpatch: don't warn about extra parentheses in staging/ This "Unnecessary parentheses" warning is disabled for drivers/staging unless the --strict option is used. Really, we don't want it at all even if the --strict option is used. Link: https://lkml.kernel.org/r/c7278d21-d96c-4c1e-b3bf-f82b8decc5df@stanley.mountain Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Andy Whitcroft <apw@canonical.com> Cc: Dwaipayan Ray <dwaipayanray1@gmail.com> Cc: Joe Perches <joe@perches.com> Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/checkpatch.pl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'scripts') diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index c625da28cdae..9d469c20871f 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5503,9 +5503,9 @@ 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; -- cgit v1.2.3 From 6494bd2d05f927fc0395c2ea11461517a9e0bb80 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:53 +0900 Subject: genksyms: fix syntax error for attribute after 'union' A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, with CONFIG_MODVERSIONS=y on v6.13-rc1: $ make -s KCFLAGS=-D__GENKSYMS__ fs/lockd/svc.i $ cat fs/lockd/svc.i | scripts/genksyms/genksyms -w [ snip ] ./include/net/addrconf.h:35: syntax error The syntax error occurs in the following code in include/net/addrconf.h: union __packed { [ snip ] }; The issue arises from __packed, which is defined as __attribute__((__packed__)), immediately after the 'union' keyword. This commit allows the 'union' keyword to be followed by attributes. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 33639232a709..a2cd035a78c9 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -236,16 +236,16 @@ type_specifier: so that it is easier to expand the definition fully later. */ | STRUCT_KEYW attribute_opt IDENT { remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; } - | UNION_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; } + | UNION_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_UNION; $$ = $3; } | ENUM_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; } /* Full definitions of an s/u/e. Record it. */ | STRUCT_KEYW attribute_opt IDENT class_body { record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; } - | UNION_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_UNION); $$ = $3; } + | UNION_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_UNION); $$ = $4; } | ENUM_KEYW IDENT enum_body { record_compound($1, $2, $3, SYM_ENUM); $$ = $3; } /* @@ -255,7 +255,7 @@ type_specifier: { add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; } /* Anonymous s/u definitions. Nothing needs doing. */ | STRUCT_KEYW attribute_opt class_body { $$ = $3; } - | UNION_KEYW class_body { $$ = $2; } + | UNION_KEYW attribute_opt class_body { $$ = $3; } ; simple_type_specifier: -- cgit v1.2.3 From c825840527813582385edca3ddeee46886527258 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:54 +0900 Subject: genksyms: fix syntax error for builtin (u)int*x*_t types A longstanding issue with genksyms is that it has hidden syntax errors. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. For example, genksyms fails to parse the following code in arch/arm64/lib/xor-neon.c: static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r) { [ snip ] } The syntax error occurs because genksyms does not recognize the uint64x2_t keyword. This commit adds support for builtin types described in Arm Neon Intrinsics Reference. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/lex.l | 1 + 1 file changed, 1 insertion(+) (limited to 'scripts') diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index a1f969dcf24f..22aeb57649d9 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -51,6 +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; -- cgit v1.2.3 From a23d4c2f5b80a8dc5f1e40658abbe5983af1a0e9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Tue, 14 Jan 2025 00:00:55 +0900 Subject: genksyms: fix syntax error for attribute before init-declarator A longstanding issue with genksyms is that it has hidden syntax errors. For example, genksyms fails to parse the following valid code: int x, __attribute__((__section__(".init.data")))y; Here, only 'y' is annotated by the attribute, although I am not aware of actual uses of this pattern in the kernel tree. When a syntax error occurs, yyerror() is called. However, error_with_pos() is a no-op unless the -w option is provided. You can observe syntax errors by manually passing the -w option. $ echo 'int x, __attribute__((__section__(".init.data")))y;' | scripts/genksyms/genksyms -w <stdin>:1: syntax error This commit allows attributes to be placed between a comma and init_declarator. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Acked-by: Nicolas Schier <n.schier@avm.de> --- scripts/genksyms/parse.y | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index a2cd035a78c9..ee600a804fa1 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -173,9 +173,9 @@ init_declarator_list: $$ = $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; @@ -186,7 +186,7 @@ init_declarator_list: add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; - $$ = $3; + $$ = $4; dont_want_type_specifier = true; } ; -- cgit v1.2.3 From a314f52a0210730d0d556de76bb7388e76d4597d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Mon, 20 Jan 2025 16:59:14 +0900 Subject: kconfig: fix file name in warnings when loading KCONFIG_DEFCONFIG_LIST Most 'make *config' commands use .config as the base configuration file. When .config does not exist, Kconfig tries to load a file listed in KCONFIG_DEFCONFIG_LIST instead. However, since commit b75b0a819af9 ("kconfig: change defconfig_list option to environment variable"), warning messages have displayed an incorrect file name in such cases. Below is a demonstration using Debian Trixie. While loading /boot/config-6.12.9-amd64, the warning messages incorrectly show .config as the file name. With this commit, the correct file name is displayed in warnings. [Before] $ rm -f .config $ make config # # using defaults found in /boot/config-6.12.9-amd64 # .config:6804:warning: symbol value 'm' invalid for FB_BACKLIGHT .config:9895:warning: symbol value 'm' invalid for ANDROID_BINDER_IPC [After] $ rm -f .config $ make config # # using defaults found in /boot/config-6.12.9-amd64 # /boot/config-6.12.9-amd64:6804:warning: symbol value 'm' invalid for FB_BACKLIGHT /boot/config-6.12.9-amd64:9895:warning: symbol value 'm' invalid for ANDROID_BINDER_IPC Fixes: b75b0a819af9 ("kconfig: change defconfig_list option to environment variable") Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- scripts/kconfig/confdata.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'scripts') diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4286d5e7f95d..3b55e7a4131d 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; } -- cgit v1.2.3 From a409fc1463d664002ea9bf700ae4674df03de111 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Mon, 20 Jan 2025 17:10:31 +0900 Subject: kconfig: fix memory leak in sym_warn_unmet_dep() The string allocated in sym_warn_unmet_dep() is never freed, leading to a memory leak when an unmet dependency is detected. Fixes: f8f69dc0b4e0 ("kconfig: make unmet dependency warnings readable") Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Reviewed-by: Petr Vorel <pvorel@suse.cz> --- scripts/kconfig/symbol.c | 1 + 1 file changed, 1 insertion(+) (limited to 'scripts') diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 89b84bf8e21f..7beb59dec5a0 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++; } -- cgit v1.2.3 From 101971298be2aa4706c8602bd81066a0f6f2ced5 Mon Sep 17 00:00:00 2001 From: Yunhui Cui <cuiyunhui@bytedance.com> Date: Wed, 14 Aug 2024 14:26:25 +0800 Subject: riscv: add a warning when physical memory address overflows The part of physical memory that exceeds the size of the linear mapping will be discarded. When the system starts up normally, a warning message will be printed to prevent confusion caused by the mismatch between the system memory and the actual physical memory. Signed-off-by: Yunhui Cui <cuiyunhui@bytedance.com> Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com> Link: https://lore.kernel.org/r/20240814062625.19794-1-cuiyunhui@bytedance.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com> --- arch/riscv/mm/init.c | 8 ++++++-- scripts/selinux/genheaders/genheaders | Bin 0 -> 90112 bytes 2 files changed, 6 insertions(+), 2 deletions(-) create mode 100755 scripts/selinux/genheaders/genheaders (limited to 'scripts') diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..9641e4ad387f 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -256,8 +256,12 @@ static void __init setup_bootmem(void) */ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; - memblock_cap_memory_range(phys_ram_base, - max_mapped_addr - phys_ram_base); + if (memblock_end_of_DRAM() > max_mapped_addr) { + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + pr_warn("Physical memory overflows the linear mapping size: region above %pa removed", + &max_mapped_addr); + } } /* diff --git a/scripts/selinux/genheaders/genheaders b/scripts/selinux/genheaders/genheaders new file mode 100755 index 000000000000..3fc32a664a79 Binary files /dev/null and b/scripts/selinux/genheaders/genheaders differ -- cgit v1.2.3 From dce4aab8441d285b9a78b33753e0bf583c1320ee Mon Sep 17 00:00:00 2001 From: Kees Cook <kees@kernel.org> Date: Mon, 27 Jan 2025 11:10:28 -0800 Subject: kbuild: Use -fzero-init-padding-bits=all GCC 15 introduces a regression in "= { 0 }" style initialization of unions that Linux has depended on for eliminating uninitialized variable contents. GCC does not seem likely to fix it[1], instead suggesting[2] that affected projects start using -fzero-init-padding-bits=unions. To avoid future surprises beyond just the current situation with unions, enable -fzero-init-padding-bits=all when available (GCC 15+). This will correctly zero padding bits in unions and structs that might have been left uninitialized, and will make sure there is no immediate regression in union initializations. As seen in the stackinit KUnit selftest union cases, which were passing before, were failing under GCC 15: not ok 18 test_small_start_old_zero ok 29 test_small_start_dynamic_partial # SKIP XFAIL uninit bytes: 63 ok 32 test_small_start_assigned_dynamic_partial # SKIP XFAIL uninit bytes: 63 ok 67 test_small_start_static_partial # SKIP XFAIL uninit bytes: 63 ok 70 test_small_start_static_all # SKIP XFAIL uninit bytes: 56 ok 73 test_small_start_dynamic_all # SKIP XFAIL uninit bytes: 56 ok 82 test_small_start_assigned_static_partial # SKIP XFAIL uninit bytes: 63 ok 85 test_small_start_assigned_static_all # SKIP XFAIL uninit bytes: 56 ok 88 test_small_start_assigned_dynamic_all # SKIP XFAIL uninit bytes: 56 The above all now pass again with -fzero-init-padding-bits=all added. This also fixes the following cases for struct initialization that had been XFAIL until now because there was no compiler support beyond the larger "-ftrivial-auto-var-init=zero" option: ok 38 test_small_hole_static_all # SKIP XFAIL uninit bytes: 3 ok 39 test_big_hole_static_all # SKIP XFAIL uninit bytes: 124 ok 40 test_trailing_hole_static_all # SKIP XFAIL uninit bytes: 7 ok 42 test_small_hole_dynamic_all # SKIP XFAIL uninit bytes: 3 ok 43 test_big_hole_dynamic_all # SKIP XFAIL uninit bytes: 124 ok 44 test_trailing_hole_dynamic_all # SKIP XFAIL uninit bytes: 7 ok 58 test_small_hole_assigned_static_all # SKIP XFAIL uninit bytes: 3 ok 59 test_big_hole_assigned_static_all # SKIP XFAIL uninit bytes: 124 ok 60 test_trailing_hole_assigned_static_all # SKIP XFAIL uninit bytes: 7 ok 62 test_small_hole_assigned_dynamic_all # SKIP XFAIL uninit bytes: 3 ok 63 test_big_hole_assigned_dynamic_all # SKIP XFAIL uninit bytes: 124 ok 64 test_trailing_hole_assigned_dynamic_all # SKIP XFAIL uninit bytes: 7 All of the above now pass when built under GCC 15. Tests can be seen with: ./tools/testing/kunit/kunit.py run stackinit --arch=x86_64 \ --make_option CC=gcc-15 Clang continues to fully initialize these kinds of variables[3] without additional flags. Suggested-by: Jakub Jelinek <jakub@redhat.com> Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118403 [1] Link: https://lore.kernel.org/linux-toolchains/Z0hRrrNU3Q+ro2T7@tucnak/ [2] Link: https://github.com/llvm/llvm-project/commit/7a086e1b2dc05f54afae3591614feede727601fa [3] Reviewed-by: Nathan Chancellor <nathan@kernel.org> Acked-by: Masahiro Yamada <masahiroy@kernel.org> Link: https://lore.kernel.org/r/20250127191031.245214-3-kees@kernel.org Signed-off-by: Kees Cook <kees@kernel.org> --- scripts/Makefile.extrawarn | 3 +++ 1 file changed, 3 insertions(+) (limited to 'scripts') diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 1d13cecc7cc7..eb719f6d8d53 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -77,6 +77,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) +# Explicitly clear padding bits during variable initialization +KBUILD_CFLAGS += $(call cc-option,-fzero-init-padding-bits=all) + KBUILD_CFLAGS += -Wextra KBUILD_CFLAGS += -Wunused -- cgit v1.2.3 From 71d815bf5dfd4f63f7557e0abe7f257c202863a1 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel <ardb@kernel.org> Date: Mon, 13 Jan 2025 16:53:07 +0100 Subject: kbuild: Strip runtime const RELA sections correctly Due to the fact that runtime const ELF sections are named without a leading period or double underscore, the RSTRIP logic that removes the static RELA sections from vmlinux fails to identify them. This results in a situation like below, where some sections that were supposed to get removed are left behind. [Nr] Name Type Address Off Size ES Flg Lk Inf Al [58] runtime_shift_d_hash_shift PROGBITS ffffffff83500f50 2900f50 000014 00 A 0 0 1 [59] .relaruntime_shift_d_hash_shift RELA 0000000000000000 55b6f00 000078 18 I 70 58 8 [60] runtime_ptr_dentry_hashtable PROGBITS ffffffff83500f68 2900f68 000014 00 A 0 0 1 [61] .relaruntime_ptr_dentry_hashtable RELA 0000000000000000 55b6f78 000078 18 I 70 60 8 [62] runtime_ptr_USER_PTR_MAX PROGBITS ffffffff83500f80 2900f80 000238 00 A 0 0 1 [63] .relaruntime_ptr_USER_PTR_MAX RELA 0000000000000000 55b6ff0 000d50 18 I 70 62 8 So tweak the match expression to strip all sections starting with .rel. While at it, consolidate the logic used by RISC-V, s390 and x86 into a single shared Makefile library command. Link: https://lore.kernel.org/all/CAHk-=wjk3ynjomNvFN8jf9A1k=qSc=JFF591W00uXj-qqNUxPQ@mail.gmail.com/ Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Charlie Jenkins <charlie@rivosinc.com> Tested-by: Charlie Jenkins <charlie@rivosinc.com> Tested-by: Alexander Gordeev <agordeev@linux.ibm.com> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> --- arch/riscv/Makefile.postlink | 8 ++------ arch/s390/Makefile.postlink | 6 +----- arch/x86/Makefile.postlink | 6 +----- scripts/Makefile.lib | 3 +++ 4 files changed, 7 insertions(+), 16 deletions(-) (limited to 'scripts') diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index 829b9abc91f6..6b0580949b6a 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -10,6 +10,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib quiet_cmd_relocs_check = CHKREL $@ cmd_relocs_check = \ @@ -19,11 +20,6 @@ ifdef CONFIG_RELOCATABLE quiet_cmd_cp_vmlinux_relocs = CPREL vmlinux.relocs cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs -quiet_cmd_relocs_strip = STRIPREL $@ -cmd_relocs_strip = $(OBJCOPY) --remove-section='.rel.*' \ - --remove-section='.rel__*' \ - --remove-section='.rela.*' \ - --remove-section='.rela__*' $@ endif # `@true` prevents complaint when there is nothing to be done @@ -33,7 +29,7 @@ vmlinux: FORCE ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) $(call if_changed,cp_vmlinux_relocs) - $(call if_changed,relocs_strip) + $(call if_changed,strip_relocs) endif clean: diff --git a/arch/s390/Makefile.postlink b/arch/s390/Makefile.postlink index df82f5410769..1ae5478cd6ac 100644 --- a/arch/s390/Makefile.postlink +++ b/arch/s390/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS=arch/s390/tools/relocs OUT_RELOCS = arch/s390/boot @@ -19,11 +20,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/relocs.S mkdir -p $(OUT_RELOCS); \ $(CMD_RELOCS) $@ > $(OUT_RELOCS)/relocs.S -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - vmlinux: FORCE $(call cmd,relocs) $(call cmd,strip_relocs) diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink index fef2e977cc7d..8b8a68162c94 100644 --- a/arch/x86/Makefile.postlink +++ b/arch/x86/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS = arch/x86/tools/relocs OUT_RELOCS = arch/x86/boot/compressed @@ -20,11 +21,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/$@.relocs $(CMD_RELOCS) $@ > $(OUT_RELOCS)/$@.relocs; \ $(CMD_RELOCS) --abs-relocs $@ -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - # `@true` prevents complaint when there is nothing to be done vmlinux: FORCE diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 7395200538da..f604f51d23ca 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -374,6 +374,9 @@ quiet_cmd_ar = AR $@ quiet_cmd_objcopy = OBJCOPY $@ cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@ +quiet_cmd_strip_relocs = RSTRIP $@ +cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $@ + # Gzip # --------------------------------------------------------------------------- -- cgit v1.2.3 From 695ed93bb30e03e9f826ee70abdd83f970741a37 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <masahiroy@kernel.org> Date: Fri, 31 Jan 2025 23:04:01 +0900 Subject: kbuild: fix Clang LTO with CONFIG_OBJTOOL=n Since commit bede169618c6 ("kbuild: enable objtool for *.mod.o and additional kernel objects"), Clang LTO builds do not perform any optimizations when CONFIG_OBJTOOL is disabled (e.g., for ARCH=arm64). This is because every LLVM bitcode file is immediately converted to ELF format before the object files are linked together. This commit fixes the breakage. Fixes: bede169618c6 ("kbuild: enable objtool for *.mod.o and additional kernel objects") Reported-by: Yonghong Song <yonghong.song@linux.dev> Signed-off-by: Masahiro Yamada <masahiroy@kernel.org> Tested-by: Yonghong Song <yonghong.song@linux.dev> --- scripts/Makefile.build | 2 ++ scripts/Makefile.lib | 10 ++++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'scripts') diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 81d9dacad03c..993708d11874 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -194,7 +194,9 @@ 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))) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index f604f51d23ca..ad55ef201aac 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -287,6 +287,8 @@ 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 @@ -302,11 +304,11 @@ endef # =========================================================================== # 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 covert 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) $@ -- cgit v1.2.3 From 04a3389b35357e9bf44533d20a80eb70d188adb8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds <torvalds@linux-foundation.org> Date: Fri, 31 Jan 2025 19:49:17 -0800 Subject: Remove stale generated 'genheaders' file This bogus stale file was added in commit 101971298be2 ("riscv: add a warning when physical memory address overflows"). It's the old location for what is now 'security/selinux/genheaders'. It looks like it got incorrectly committed back when that file was in the old location, and then rebasing kept the bogus file alive. Reported-by: Eric Biggers <ebiggers@kernel.org> Link: https://lore.kernel.org/linux-riscv/20250201020003.GA77370@sol.localdomain/ Fixes: 101971298be2 ("riscv: add a warning when physical memory address overflows") Cc: Palmer Dabbelt <palmer@rivosinc.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- scripts/selinux/genheaders/genheaders | Bin 90112 -> 0 bytes 1 file changed, 0 insertions(+), 0 deletions(-) delete mode 100755 scripts/selinux/genheaders/genheaders (limited to 'scripts') diff --git a/scripts/selinux/genheaders/genheaders b/scripts/selinux/genheaders/genheaders deleted file mode 100755 index 3fc32a664a79..000000000000 Binary files a/scripts/selinux/genheaders/genheaders and /dev/null differ -- cgit v1.2.3 From 4ebc417ef9cb34010a71270421fe320ec5d88aa2 Mon Sep 17 00:00:00 2001 From: Jan Kiszka <jan.kiszka@siemens.com> Date: Fri, 10 Jan 2025 11:36:33 +0100 Subject: scripts/gdb: fix aarch64 userspace detection in get_current_task At least recent gdb releases (seen with 14.2) return SP_EL0 as signed long which lets the right-shift always return 0. Link: https://lkml.kernel.org/r/dcd2fabc-9131-4b48-8419-6444e2d67454@siemens.com Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Cc: Barry Song <baohua@kernel.org> Cc: Kieran Bingham <kbingham@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- scripts/gdb/linux/cpus.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts') diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 2f11c4f9c345..13eb8b3901b8 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -167,7 +167,7 @@ def get_current_task(cpu): var_ptr = gdb.parse_and_eval("&pcpu_hot.current_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() -- cgit v1.2.3