Add CONFIG_KALLSYMS_LINEINFO, which embeds a compact address-to-line
lookup table in the kernel image so stack traces directly print source
file and line number information:
root@localhost:~# echo c > /proc/sysrq-trigger
[ 11.201987] sysrq: Trigger a crash
[ 11.202831] Kernel panic - not syncing: sysrq triggered crash
[ 11.206218] Call Trace:
[ 11.206501] <TASK>
[ 11.206749] dump_stack_lvl+0x5d/0x80 (lib/dump_stack.c:94)
[ 11.207403] vpanic+0x36e/0x620 (kernel/panic.c:650)
[ 11.208565] ? __lock_acquire+0x465/0x2240 (kernel/locking/lockdep.c:4674)
[ 11.209324] panic+0xc9/0xd0 (kernel/panic.c:787)
[ 11.211873] ? find_held_lock+0x2b/0x80 (kernel/locking/lockdep.c:5350)
[ 11.212597] ? lock_release+0xd3/0x300 (kernel/locking/lockdep.c:5535)
[ 11.213312] sysrq_handle_crash+0x1a/0x20 (drivers/tty/sysrq.c:154)
[ 11.214005] __handle_sysrq.cold+0x66/0x256 (drivers/tty/sysrq.c:611)
[ 11.214712] write_sysrq_trigger+0x65/0x80 (drivers/tty/sysrq.c:1221)
[ 11.215424] proc_reg_write+0x1bd/0x3c0 (fs/proc/inode.c:330)
[ 11.216061] vfs_write+0x1c6/0xff0 (fs/read_write.c:686)
[ 11.218848] ksys_write+0xfa/0x200 (fs/read_write.c:740)
[ 11.222394] do_syscall_64+0xf3/0x690 (arch/x86/entry/syscall_64.c:63)
[ 11.223942] entry_SYSCALL_64_after_hwframe+0x77/0x7f
(arch/x86/entry/entry_64.S:121)
At build time, a new host tool (scripts/gen_lineinfo) reads DWARF
.debug_line from vmlinux using libdw (elfutils), extracts all
address-to-file:line mappings, and generates an assembly file with
sorted parallel arrays (offsets from _text, file IDs, and line
numbers). These are linked into vmlinux as .rodata.
At runtime, kallsyms_lookup_lineinfo() does a binary search on the
table and __sprint_symbol() appends "(file:line)" to each stack frame.
The lookup uses offsets from _text so it works with KASLR, requires no
locks or allocations, and is safe in any context including panic.
The feature requires CONFIG_DEBUG_INFO (for DWARF data) and libelf
and libdw (from elfutils) on the build host.
Memory footprint, measured with:
make ARCH=x86_64 O=$B defconfig
./scripts/config --file $B/.config -e DEBUG_INFO \
-e DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT
make ARCH=x86_64 O=$B olddefconfig && make ARCH=x86_64 O=$B -j$(nproc)
strip -g $B/vmlinux -o vmlinux.nodbg && stat -c %s vmlinux.nodbg
Table: 1,794,950 entries from 4,232 source files
lineinfo_addrs[] 1,794,950 x u32 = 6.8 MiB
lineinfo_file_ids[] 1,794,950 x u16 = 3.4 MiB
lineinfo_lines[] 1,794,950 x u32 = 6.8 MiB
file_offsets + filenames = 0.1 MiB
Total .rodata increase: = 17.2 MiB
vmlinux (stripped): 51.1 MiB -> 69.1 MiB (+18.0 MiB / +35.3%)
That is the cost of the uncompressed format introduced here; the delta
compression added later in this series brings it down to +8.0 MiB
(+15.7%) on the same config.
Suggested-by: Petr Pavlu <[email protected]>
Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Sasha Levin <[email protected]>
---
Documentation/admin-guide/index.rst | 1 +
.../admin-guide/kallsyms-lineinfo.rst | 72 ++
MAINTAINERS | 6 +
include/linux/kallsyms.h | 18 +-
init/Kconfig | 20 +
kernel/kallsyms.c | 101 +-
kernel/kallsyms_internal.h | 9 +
scripts/.gitignore | 1 +
scripts/Makefile | 3 +
scripts/empty_lineinfo.S | 30 +
scripts/gen_lineinfo.c | 969 ++++++++++++++++++
scripts/kallsyms.c | 11 +
scripts/link-vmlinux.sh | 43 +-
13 files changed, 1273 insertions(+), 11 deletions(-)
create mode 100644 Documentation/admin-guide/kallsyms-lineinfo.rst
create mode 100644 scripts/empty_lineinfo.S
create mode 100644 scripts/gen_lineinfo.c
diff --git a/Documentation/admin-guide/index.rst
b/Documentation/admin-guide/index.rst
index cd28dfe91b06..37456e08fe43 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -73,6 +73,7 @@ problems and bugs in particular.
ramoops
dynamic-debug-howto
init
+ kallsyms-lineinfo
kdump/index
perf/index
pstore-blk
diff --git a/Documentation/admin-guide/kallsyms-lineinfo.rst
b/Documentation/admin-guide/kallsyms-lineinfo.rst
new file mode 100644
index 000000000000..4c5de44e68fc
--- /dev/null
+++ b/Documentation/admin-guide/kallsyms-lineinfo.rst
@@ -0,0 +1,72 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================
+Kallsyms Source Line Info (LINEINFO)
+====================================
+
+Overview
+========
+
+``CONFIG_KALLSYMS_LINEINFO`` embeds DWARF-derived source file and line number
+mappings into the kernel image so that stack traces include
+``(file.c:123)`` annotations next to each symbol. This makes it significantly
+easier to pinpoint the exact source location during debugging, without needing
+to manually cross-reference addresses with ``addr2line``.
+
+Enabling the Feature
+====================
+
+Enable the following kernel configuration options::
+
+ CONFIG_KALLSYMS=y
+ CONFIG_DEBUG_INFO=y
+ CONFIG_KALLSYMS_LINEINFO=y
+
+Build dependency: the host tool ``scripts/gen_lineinfo`` requires ``libelf``
+and ``libdw`` from elfutils. Install the development packages:
+
+- Debian/Ubuntu: ``apt install libdw-dev libelf-dev``
+- Fedora/RHEL: ``dnf install elfutils-devel elfutils-libelf-devel``
+- Arch Linux: ``pacman -S libelf``
+
+Example Output
+==============
+
+Without ``CONFIG_KALLSYMS_LINEINFO``::
+
+ Call Trace:
+ <TASK>
+ dump_stack_lvl+0x5d/0x80
+ do_syscall_64+0x82/0x190
+ entry_SYSCALL_64_after_hwframe+0x76/0x7e
+
+With ``CONFIG_KALLSYMS_LINEINFO``::
+
+ Call Trace:
+ <TASK>
+ dump_stack_lvl+0x5d/0x80 (lib/dump_stack.c:123)
+ do_syscall_64+0x82/0x190 (arch/x86/entry/common.c:52)
+ entry_SYSCALL_64_after_hwframe+0x76/0x7e
+
+Note that assembly routines (such as ``entry_SYSCALL_64_after_hwframe``) are
+not annotated because they lack DWARF debug information.
+
+Memory Overhead
+===============
+
+The lineinfo tables are stored in ``.rodata`` and typically add approximately
+44 MiB to the kernel image for a standard configuration (~4.6 million DWARF
+line entries, ~10 bytes per entry after deduplication).
+
+Known Limitations
+=================
+
+- **vmlinux only**: Only symbols in the core kernel image are annotated.
+ Module symbols are not covered.
+- **4 GiB offset limit**: Address offsets from ``_text`` are stored as 32-bit
+ values. Entries beyond 4 GiB from ``_text`` are skipped at build time with
+ a warning.
+- **65535 file limit**: Source file IDs are stored as 16-bit values. Builds
+ with more than 65535 unique source files will fail with an error.
+- **No assembly annotations**: Functions implemented in assembly that lack
+ DWARF ``.debug_line`` data are not annotated.
diff --git a/MAINTAINERS b/MAINTAINERS
index 4a8b0fd665ce..b98d57b1ee1d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13931,6 +13931,12 @@ S: Maintained
F: Documentation/hwmon/k8temp.rst
F: drivers/hwmon/k8temp.c
+KALLSYMS LINEINFO
+M: Sasha Levin <[email protected]>
+S: Maintained
+F: Documentation/admin-guide/kallsyms-lineinfo.rst
+F: scripts/gen_lineinfo.c
+
KASAN
M: Andrey Ryabinin <[email protected]>
R: Alexander Potapenko <[email protected]>
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index d5dd54c53ace..53cc25a6e85d 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -16,10 +16,15 @@
#include <asm/sections.h>
#define KSYM_NAME_LEN 512
+
+/* Extra space for " (path/to/file.c:12345)" suffix when lineinfo is enabled */
+#define KSYM_LINEINFO_LEN (IS_ENABLED(CONFIG_KALLSYMS_LINEINFO) ? 128 : 0)
+
#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \
(KSYM_NAME_LEN - 1) + \
2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \
- (BUILD_ID_SIZE_MAX * 2) + 1)
+ (BUILD_ID_SIZE_MAX * 2) + 1 + \
+ KSYM_LINEINFO_LEN)
struct cred;
struct module;
@@ -96,6 +101,9 @@ extern int sprint_backtrace_build_id(char *buffer, unsigned
long address);
int lookup_symbol_name(unsigned long addr, char *symname);
+bool kallsyms_lookup_lineinfo(unsigned long addr, unsigned long sym_start,
+ const char **file, unsigned int *line);
+
#else /* !CONFIG_KALLSYMS */
static inline unsigned long kallsyms_lookup_name(const char *name)
@@ -164,6 +172,14 @@ static inline int kallsyms_on_each_match_symbol(int
(*fn)(void *, unsigned long)
{
return -EOPNOTSUPP;
}
+
+static inline bool kallsyms_lookup_lineinfo(unsigned long addr,
+ unsigned long sym_start,
+ const char **file,
+ unsigned int *line)
+{
+ return false;
+}
#endif /*CONFIG_KALLSYMS*/
static inline void print_ip_sym(const char *loglvl, unsigned long ip)
diff --git a/init/Kconfig b/init/Kconfig
index 5230d4879b1c..635305ec0594 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2087,6 +2087,26 @@ config KALLSYMS_ALL
Say N unless you really need all symbols, or kernel live patching.
+config KALLSYMS_LINEINFO
+ bool "Embed source file:line information in stack traces"
+ depends on KALLSYMS && DEBUG_INFO
+ help
+ Embeds an address-to-source-line mapping table in the kernel
+ image so that stack traces directly include file:line information,
+ similar to what scripts/decode_stacktrace.sh provides but without
+ needing external tools or a vmlinux with debug info at runtime.
+
+ When enabled, stack traces will look like:
+
+ kmem_cache_alloc_noprof+0x60/0x630 (mm/slub.c:3456)
+ anon_vma_clone+0x2ed/0xcf0 (mm/rmap.c:412)
+
+ This requires libelf and libdw (from elfutils) on the build host.
+ Costs 10 bytes per DWARF line-table entry; for x86_64_defconfig
+ with CONFIG_DEBUG_INFO that is about 18MB.
+
+ If unsure, say N.
+
# end of the "standard kernel features (expert users)" menu
config ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index aec2f06858af..baf52e81118b 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -467,13 +467,82 @@ static int append_buildid(char *buffer, const char
*modname,
#endif /* CONFIG_STACKTRACE_BUILD_ID */
+bool kallsyms_lookup_lineinfo(unsigned long addr, unsigned long sym_start,
+ const char **file, unsigned int *line)
+{
+ unsigned long raw_offset, raw_min;
+ unsigned int offset, min_offset = 0, low, high, mid, file_id;
+
+ if (!IS_ENABLED(CONFIG_KALLSYMS_LINEINFO) || !lineinfo_num_entries)
+ return false;
+
+ /* Compute offset from _text */
+ if (addr < (unsigned long)_text)
+ return false;
+
+ /*
+ * Round-trip through unsigned int rather than comparing against
+ * UINT_MAX: unsigned long is already 32 bits on 32-bit targets, so
+ * that comparison would be dead code there.
+ */
+ raw_offset = addr - (unsigned long)_text;
+ offset = raw_offset;
+ if (offset != raw_offset)
+ return false;
+
+ /*
+ * The search below returns the closest entry at or below @offset, so
+ * a symbol without line entries of its own (assembly without debug
+ * info, or anything past the _etext cap like .init.text) would
+ * inherit the last entry of whatever precedes it. Bound the result
+ * to entries at or above the resolved symbol's start.
+ */
+ if (sym_start > (unsigned long)_text) {
+ raw_min = sym_start - (unsigned long)_text;
+
+ if (raw_min <= raw_offset)
+ min_offset = raw_min;
+ }
+
+ /* Binary search for largest entry <= offset */
+ low = 0;
+ high = lineinfo_num_entries;
+ while (low < high) {
+ mid = low + (high - low) / 2;
+ if (lineinfo_addrs[mid] <= offset)
+ low = mid + 1;
+ else
+ high = mid;
+ }
+
+ if (low == 0)
+ return false;
+ low--;
+
+ if (lineinfo_addrs[low] < min_offset)
+ return false;
+
+ file_id = lineinfo_file_ids[low];
+ *line = lineinfo_lines[low];
+
+ if (file_id >= lineinfo_num_files)
+ return false;
+
+ if (lineinfo_file_offsets[file_id] >= lineinfo_filenames_size)
+ return false;
+
+ *file = &lineinfo_filenames[lineinfo_file_offsets[file_id]];
+ return true;
+}
+
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
- int symbol_offset, int add_offset, int add_buildid)
+ int symbol_offset, int add_offset, int add_buildid,
+ int add_lineinfo)
{
char *modname;
const unsigned char *buildid;
- unsigned long offset, size;
+ unsigned long offset, size, sym_start;
int len;
/* Prevent module removal until modname and modbuildid are printed */
@@ -485,6 +554,7 @@ static int __sprint_symbol(char *buffer, unsigned long
address,
if (!len)
return sprintf(buffer, "0x%lx", address - symbol_offset);
+ sym_start = address - offset;
offset -= symbol_offset;
if (add_offset)
@@ -497,6 +567,23 @@ static int __sprint_symbol(char *buffer, unsigned long
address,
len += sprintf(buffer + len, "]");
}
+ /*
+ * Append "(file:line)" only for stack-backtrace consumers. Plain
+ * sprint_symbol() backs %ps, and many existing format strings tack
+ * literal "()" after %ps to indicate a function call ("foo()
+ * replaced with bar()"); appending lineinfo there would produce a
+ * confusing "foo (file:line)()".
+ */
+ if (add_lineinfo && IS_ENABLED(CONFIG_KALLSYMS_LINEINFO) && !modname) {
+ const char *li_file;
+ unsigned int li_line;
+
+ if (kallsyms_lookup_lineinfo(address, sym_start,
+ &li_file, &li_line))
+ len += snprintf(buffer + len, KSYM_SYMBOL_LEN - len,
+ " (%s:%u)", li_file, li_line);
+ }
+
return len;
}
@@ -513,7 +600,7 @@ static int __sprint_symbol(char *buffer, unsigned long
address,
*/
int sprint_symbol(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0, 1, 0);
+ return __sprint_symbol(buffer, address, 0, 1, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol);
@@ -530,7 +617,7 @@ EXPORT_SYMBOL_GPL(sprint_symbol);
*/
int sprint_symbol_build_id(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0, 1, 1);
+ return __sprint_symbol(buffer, address, 0, 1, 1, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_build_id);
@@ -547,7 +634,7 @@ EXPORT_SYMBOL_GPL(sprint_symbol_build_id);
*/
int sprint_symbol_no_offset(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0, 0, 0);
+ return __sprint_symbol(buffer, address, 0, 0, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
@@ -567,7 +654,7 @@ EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, -1, 1, 0);
+ return __sprint_symbol(buffer, address, -1, 1, 0, 1);
}
/**
@@ -587,7 +674,7 @@ int sprint_backtrace(char *buffer, unsigned long address)
*/
int sprint_backtrace_build_id(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, -1, 1, 1);
+ return __sprint_symbol(buffer, address, -1, 1, 1, 1);
}
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h
index 81a867dbe57d..d7374ce444d8 100644
--- a/kernel/kallsyms_internal.h
+++ b/kernel/kallsyms_internal.h
@@ -15,4 +15,13 @@ extern const u16 kallsyms_token_index[];
extern const unsigned int kallsyms_markers[];
extern const u8 kallsyms_seqs_of_names[];
+extern const u32 lineinfo_num_entries;
+extern const u32 lineinfo_addrs[];
+extern const u16 lineinfo_file_ids[];
+extern const u32 lineinfo_lines[];
+extern const u32 lineinfo_num_files;
+extern const u32 lineinfo_file_offsets[];
+extern const u32 lineinfo_filenames_size;
+extern const char lineinfo_filenames[];
+
#endif // LINUX_KALLSYMS_INTERNAL_H_
diff --git a/scripts/.gitignore b/scripts/.gitignore
index 4215c2208f7e..e175714c18b6 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
/asn1_compiler
+/gen_lineinfo
/gen_packed_field_checks
/generate_rust_target
/insert-sys-cert
diff --git a/scripts/Makefile b/scripts/Makefile
index 3434a82a119f..976c607c8d96 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -4,6 +4,7 @@
# the kernel for the build process.
hostprogs-always-$(CONFIG_KALLSYMS) += kallsyms
+hostprogs-always-$(CONFIG_KALLSYMS_LINEINFO) += gen_lineinfo
hostprogs-always-$(BUILD_C_RECORDMCOUNT) += recordmcount
hostprogs-always-$(CONFIG_BUILDTIME_TABLE_SORT) += sorttable
hostprogs-always-$(CONFIG_ASN1) += asn1_compiler
@@ -37,6 +38,8 @@ HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
HOSTCFLAGS_sign-file.o = $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2>
/dev/null)
HOSTCFLAGS_sign-file.o += -I$(srctree)/tools/include/uapi/
HOSTLDLIBS_sign-file = $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null
|| echo -lcrypto)
+HOSTCFLAGS_gen_lineinfo.o = $(shell $(HOSTPKG_CONFIG) --cflags libdw 2>
/dev/null)
+HOSTLDLIBS_gen_lineinfo = $(shell $(HOSTPKG_CONFIG) --libs libdw 2> /dev/null
|| echo -ldw -lelf)
ifdef CONFIG_UNWINDER_ORC
ifeq ($(ARCH),x86_64)
diff --git a/scripts/empty_lineinfo.S b/scripts/empty_lineinfo.S
new file mode 100644
index 000000000000..e058c4113712
--- /dev/null
+++ b/scripts/empty_lineinfo.S
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2026 Sasha Levin <[email protected]>
+ *
+ * Empty lineinfo stub for the initial vmlinux link.
+ * The real lineinfo is generated from .tmp_vmlinux1 by gen_lineinfo.
+ */
+ .section .rodata, "a"
+ .globl lineinfo_num_entries
+ .balign 4
+lineinfo_num_entries:
+ .long 0
+ .globl lineinfo_num_files
+ .balign 4
+lineinfo_num_files:
+ .long 0
+ .globl lineinfo_addrs
+lineinfo_addrs:
+ .globl lineinfo_file_ids
+lineinfo_file_ids:
+ .globl lineinfo_lines
+lineinfo_lines:
+ .globl lineinfo_file_offsets
+lineinfo_file_offsets:
+ .globl lineinfo_filenames_size
+ .balign 4
+lineinfo_filenames_size:
+ .long 0
+ .globl lineinfo_filenames
+lineinfo_filenames:
diff --git a/scripts/gen_lineinfo.c b/scripts/gen_lineinfo.c
new file mode 100644
index 000000000000..a3ee54eaad05
--- /dev/null
+++ b/scripts/gen_lineinfo.c
@@ -0,0 +1,969 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * gen_lineinfo.c - Generate address-to-source-line lookup tables from DWARF
+ *
+ * Copyright (C) 2026 Sasha Levin <[email protected]>
+ *
+ * Reads DWARF .debug_line from a vmlinux ELF file and outputs an assembly
+ * file containing sorted lookup tables that the kernel uses to annotate
+ * stack traces with source file:line information.
+ *
+ * Requires libelf and libdw from elfutils.
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <elfutils/libdw.h>
+#include <dwarf.h>
+#include <elf.h>
+#include <gelf.h>
+#include <limits.h>
+#include <array_size.h>
+#include <hash.h>
+#include <hashtable.h>
+#include <xalloc.h>
+
+#define LINEINFO_PREFIX "gen_lineinfo: "
+
+static bool verbose;
+
+#define verbose_msg(fmt, ...) \
+ do { \
+ if (verbose) \
+ fprintf(stderr, LINEINFO_PREFIX fmt "\n", \
+ ##__VA_ARGS__); \
+ } while (0)
+
+#define warn(fmt, ...) \
+ fprintf(stderr, LINEINFO_PREFIX "warning: " fmt "\n", ##__VA_ARGS__)
+
+#define error(fmt, ...)
\
+ do { \
+ fprintf(stderr, LINEINFO_PREFIX "error: " fmt "\n", \
+ ##__VA_ARGS__); \
+ exit(1); \
+ } while (0)
+
+static unsigned int skipped_overflow;
+
+/*
+ * vmlinux mode: end of the invariant .text region. Zero means "no cap"
+ * (graceful fallback when _etext is absent on some build).
+ */
+static unsigned long long text_end_addr;
+
+struct line_entry {
+ unsigned int offset; /* offset from _text */
+ unsigned int file_id;
+ unsigned int line;
+};
+
+/*
+ * Individually allocated so files[] can grow without invalidating the
+ * hlist_node linkage.
+ */
+struct file_entry {
+ struct hlist_node hnode;
+ unsigned int id;
+ unsigned int str_offset;
+ char name[];
+};
+
+static struct line_entry *entries;
+static unsigned int num_entries;
+static unsigned int entries_capacity;
+
+static struct file_entry **files;
+static unsigned int num_files;
+static unsigned int files_capacity;
+
+static HASHTABLE_DEFINE(file_hashtable, 1U << 13);
+
+static void add_entry(unsigned int offset, unsigned int file_id,
+ unsigned int line)
+{
+ if (num_entries >= entries_capacity) {
+ entries_capacity = entries_capacity ? entries_capacity * 2 :
65536;
+ entries = xrealloc(entries, entries_capacity *
sizeof(*entries));
+ }
+ entries[num_entries].offset = offset;
+ entries[num_entries].file_id = file_id;
+ entries[num_entries].line = line;
+ num_entries++;
+}
+
+static unsigned int find_or_add_file(const char *name)
+{
+ unsigned int key = hash_str(name);
+ struct file_entry *f;
+ size_t len;
+
+ hash_for_each_possible(file_hashtable, f, hnode, key)
+ if (!strcmp(f->name, name))
+ return f->id;
+
+ if (num_files >= 65535)
+ error("too many source files (%u > 65535)", num_files);
+
+ if (num_files >= files_capacity) {
+ files_capacity = files_capacity ? files_capacity * 2 : 4096;
+ files = xrealloc(files, files_capacity * sizeof(*files));
+ }
+
+ len = strlen(name);
+ f = xmalloc(sizeof(*f) + len + 1);
+ memset(f, 0, sizeof(*f));
+ memcpy(f->name, name, len + 1);
+ f->id = num_files;
+
+ files[num_files] = f;
+ hash_add(file_hashtable, &f->hnode, key);
+
+ return num_files++;
+}
+
+/*
+ * Well-known top-level directories in the kernel source tree. Only used
+ * as a last resort, when a path matches none of the build roots below --
+ * e.g. an object compiled outside any of them.
+ */
+static const char * const kernel_dirs[] = {
+ "arch/", "block/", "certs/", "crypto/", "drivers/", "fs/",
+ "include/", "init/", "io_uring/", "ipc/", "kernel/", "lib/",
+ "mm/", "net/", "rust/", "samples/", "scripts/", "security/",
+ "sound/", "tools/", "usr/", "virt/",
+};
+
+/* Absolute build and source roots, longest first. */
+struct path_root {
+ char *path;
+ size_t len;
+};
+
+static struct path_root path_roots[8];
+static unsigned int num_path_roots;
+
+/*
+ * Lexically canonicalize @path in place: collapse repeated slashes, drop
+ * "." components and resolve ".." against the preceding component. Purely
+ * textual -- nothing is stat()ed, because DWARF can name generated files
+ * that do not exist yet when gen_lineinfo runs.
+ */
+static void normalize_path(char *path)
+{
+ bool absolute = path[0] == '/';
+ char *base, *out = path;
+ const char *in = path;
+
+ if (absolute)
+ *out++ = *in++;
+ base = out;
+
+ while (*in) {
+ const char *seg = in;
+ size_t seglen;
+
+ while (*in && *in != '/')
+ in++;
+ seglen = in - seg;
+ while (*in == '/')
+ in++;
+
+ if (!seglen || (seglen == 1 && seg[0] == '.'))
+ continue;
+
+ if (seglen == 2 && seg[0] == '.' && seg[1] == '.') {
+ if (out > base) {
+ /* Pop the previously emitted component. */
+ while (out > base && out[-1] != '/')
+ out--;
+ if (out > base)
+ out--; /* and its separator */
+ continue;
+ }
+ /* "/.." is "/"; a leading ".." in a relative path
stays. */
+ if (absolute)
+ continue;
+ }
+
+ /*
+ * Separator first: writing it after the component would land
+ * on the byte @in still points at whenever nothing has been
+ * compacted yet, clobbering the terminator and running the
+ * loop off the end of the string.
+ */
+ if (out > base)
+ *out++ = '/';
+ memmove(out, seg, seglen);
+ out += seglen;
+ }
+
+ if (out == base && !absolute)
+ *out++ = '.';
+ *out = '\0';
+}
+
+static int compare_path_roots(const void *a, const void *b)
+{
+ const struct path_root *ra = a, *rb = b;
+
+ if (ra->len != rb->len)
+ return ra->len > rb->len ? -1 : 1;
+ return 0;
+}
+
+static void add_path_root(const char *path)
+{
+ char buf[PATH_MAX];
+
+ if (!path || !*path)
+ return;
+
+ if (path[0] == '/') {
+ if (snprintf(buf, sizeof(buf), "%s", path) >= (int)sizeof(buf))
+ return;
+ } else {
+ char cwd[PATH_MAX];
+
+ /* kbuild runs host tools with cwd == $objtree. */
+ if (!getcwd(cwd, sizeof(cwd)))
+ return;
+ if (snprintf(buf, sizeof(buf), "%s/%s", cwd, path) >=
(int)sizeof(buf))
+ return;
+ }
+
+ normalize_path(buf);
+
+ /* "/" would match every absolute path. */
+ if (!strcmp(buf, "/"))
+ return;
+
+ for (unsigned int i = 0; i < num_path_roots; i++)
+ if (!strcmp(path_roots[i].path, buf))
+ return;
+
+ if (num_path_roots == ARRAY_SIZE(path_roots))
+ return;
+
+ path_roots[num_path_roots].path = xstrdup(buf);
+ path_roots[num_path_roots].len = strlen(buf);
+ num_path_roots++;
+}
+
+/*
+ * Collect the roots that DWARF paths get made relative to. kbuild exports
+ * all three, so no Makefile plumbing is needed: $objtree and $srctree cover
+ * in-tree and O= builds, and $srcroot covers M= external modules, whose
+ * sources live under neither.
+ */
+static void init_path_roots(void)
+{
+ static const char * const vars[] = { "objtree", "srctree", "srcroot" };
+
+ for (unsigned int i = 0; i < ARRAY_SIZE(vars); i++) {
+ const char *val = getenv(vars[i]);
+ char *real;
+
+ if (!val || !*val)
+ continue;
+
+ add_path_root(val);
+
+ /*
+ * Register the resolved form as well, so a symlinked tree
+ * matches whichever spelling the compiler recorded. Only
+ * the roots are resolved this way -- never a DWARF path.
+ */
+ real = realpath(val, NULL);
+ if (real) {
+ add_path_root(real);
+ free(real);
+ }
+ }
+
+ qsort(path_roots, num_path_roots, sizeof(*path_roots),
+ compare_path_roots);
+}
+
+/*
+ * Strip a DWARF filename down to a kernel-tree-relative path.
+ *
+ * Per DWARF, a relative DW_AT_name is relative to the CU's DW_AT_comp_dir,
+ * so the two are joined and canonicalized first. The result is then made
+ * relative to the longest matching build root. Everything after that is a
+ * fallback for objects built outside the tree.
+ */
+static const char *make_relative(const char *path, const char *comp_dir)
+{
+ static char buf[PATH_MAX];
+ const char *p;
+
+ if (path[0] == '/') {
+ if (snprintf(buf, sizeof(buf), "%s", path) >= (int)sizeof(buf))
+ return path;
+ } else if (comp_dir && comp_dir[0] == '/') {
+ if (snprintf(buf, sizeof(buf), "%s/%s", comp_dir, path) >=
+ (int)sizeof(buf))
+ return path;
+ } else {
+ /* Nothing absolute to anchor against. */
+ return path;
+ }
+
+ normalize_path(buf);
+
+ for (unsigned int i = 0; i < num_path_roots; i++) {
+ size_t len = path_roots[i].len;
+
+ if (!strncmp(buf, path_roots[i].path, len) && buf[len] == '/')
+ return buf + len + 1;
+ }
+
+ /*
+ * comp_dir may still be a usable prefix even when it is not one of
+ * the roots -- but only if stripping it leaves a directory
+ * component, otherwise the kernel_dirs scan recovers more.
+ */
+ if (comp_dir) {
+ size_t len = strlen(comp_dir);
+
+ if (!strncmp(buf, comp_dir, len) && buf[len] == '/' &&
+ strchr(buf + len + 1, '/'))
+ return buf + len + 1;
+ }
+
+ for (p = strchr(buf, '/'); p; p = strchr(p + 1, '/'))
+ for (unsigned int i = 0; i < ARRAY_SIZE(kernel_dirs); i++)
+ if (!strncmp(p + 1, kernel_dirs[i],
+ strlen(kernel_dirs[i])))
+ return p + 1;
+
+ p = strrchr(buf, '/');
+ return p ? p + 1 : buf;
+}
+
+static int compare_entries(const void *a, const void *b)
+{
+ const struct line_entry *ea = a;
+ const struct line_entry *eb = b;
+
+ if (ea->offset != eb->offset)
+ return ea->offset < eb->offset ? -1 : 1;
+ if (ea->file_id != eb->file_id)
+ return ea->file_id < eb->file_id ? -1 : 1;
+ if (ea->line != eb->line)
+ return ea->line < eb->line ? -1 : 1;
+ return 0;
+}
+
+/*
+ * Look up a vmlinux symbol by exact name and return its st_value, or
+ * @fallback if absent. Aborts when @required and the symbol is missing.
+ */
+static unsigned long long find_vmlinux_sym(Elf *elf, const char *name,
+ unsigned long long fallback,
+ bool required)
+{
+ size_t nsyms, i;
+ Elf_Scn *scn = NULL;
+ GElf_Shdr shdr;
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ Elf_Data *data;
+
+ if (!gelf_getshdr(scn, &shdr))
+ continue;
+ if (shdr.sh_type != SHT_SYMTAB)
+ continue;
+
+ data = elf_getdata(scn, NULL);
+ if (!data)
+ continue;
+
+ nsyms = shdr.sh_size / shdr.sh_entsize;
+ for (i = 0; i < nsyms; i++) {
+ GElf_Sym sym;
+ const char *sname;
+
+ if (!gelf_getsym(data, i, &sym))
+ continue;
+ sname = elf_strptr(elf, shdr.sh_link, sym.st_name);
+ if (sname && !strcmp(sname, name))
+ return sym.st_value;
+ }
+ }
+
+ if (required)
+ error("cannot find %s symbol", name);
+ return fallback;
+}
+
+static unsigned long long find_text_addr(Elf *elf)
+{
+ return find_vmlinux_sym(elf, "_text", 0, true);
+}
+
+/*
+ * vmlinux is linked in multiple passes: gen_lineinfo runs against
+ * .tmp_vmlinux1 (which carries an empty lineinfo stub), then real tables
+ * are linked in for the final image. Sections placed AFTER .rodata
+ * (.init.text, .exit.text, ...) shift forward as .rodata grows to hold
+ * the real lineinfo blob, so DWARF addresses we'd capture for them in
+ * pass 1 would be stale in the final kernel. Cap captured addresses at
+ * _etext, the symbol that marks the end of .text — placed before .rodata
+ * in every architecture's vmlinux.lds.S, so its addresses are invariant
+ * across the relink. Returns 0 if _etext is absent (no cap; v3 behavior).
+ */
+static unsigned long long find_text_end_addr(Elf *elf)
+{
+ return find_vmlinux_sym(elf, "_etext", 0, false);
+}
+
+static int compare_uints(const void *a, const void *b)
+{
+ unsigned int ua = *(const unsigned int *)a;
+ unsigned int ub = *(const unsigned int *)b;
+
+ if (ua != ub)
+ return ua < ub ? -1 : 1;
+ return 0;
+}
+
+/* Sorted, duplicate-free extents of every function symbol. */
+struct sym_start {
+ unsigned int offset;
+ unsigned int size;
+};
+
+static struct sym_start *sym_starts;
+static unsigned int num_sym_starts;
+static unsigned int sym_starts_capacity;
+
+/* Sorted offsets one past the end of each DWARF line-program sequence. */
+static unsigned int *seq_ends;
+static unsigned int num_seq_ends;
+static unsigned int seq_ends_capacity;
+
+static void append_offset(unsigned int **arr, unsigned int *count,
+ unsigned int *capacity, unsigned int value)
+{
+ if (*count >= *capacity) {
+ *capacity = *capacity ? *capacity * 2 : 16384;
+ *arr = xrealloc(*arr, *capacity * sizeof(**arr));
+ }
+ (*arr)[(*count)++] = value;
+}
+
+static void sort_unique(unsigned int *arr, unsigned int *count)
+{
+ unsigned int j = 0;
+
+ if (*count < 2)
+ return;
+
+ qsort(arr, *count, sizeof(*arr), compare_uints);
+ for (unsigned int i = 1; i < *count; i++) {
+ if (arr[i] == arr[j])
+ continue;
+ if (++j != i)
+ arr[j] = arr[i];
+ }
+ *count = j + 1;
+}
+
+/*
+ * Record the end of a line-program sequence. @addr is one past the last
+ * covered byte, so the sequence's own coverage is tested using addr - 1.
+ */
+static void record_seq_end(unsigned long long addr,
+ unsigned long long text_addr)
+{
+ unsigned long long raw;
+
+ if (addr <= text_addr)
+ return;
+ if (text_end_addr && addr - 1 >= text_end_addr)
+ return;
+
+ raw = addr - text_addr;
+ if (raw > UINT_MAX)
+ return;
+
+ append_offset(&seq_ends, &num_seq_ends, &seq_ends_capacity,
+ (unsigned int)raw);
+}
+
+static int compare_sym_starts(const void *a, const void *b)
+{
+ const struct sym_start *sa = a, *sb = b;
+
+ if (sa->offset != sb->offset)
+ return sa->offset < sb->offset ? -1 : 1;
+ /* Larger extent first, so the dedup below keeps it. */
+ if (sa->size != sb->size)
+ return sa->size > sb->size ? -1 : 1;
+ return 0;
+}
+
+/*
+ * Collect the extent of every function symbol. deduplicate() uses these to
+ * make sure each function keeps an entry at its own first byte; without that
+ * the kernel's symbol-boundary check rejects the preceding function's entry
+ * and the frame goes unannotated.
+ */
+static void collect_symbol_starts(Elf *elf, unsigned long long text_addr)
+{
+ Elf_Scn *scn = NULL;
+ GElf_Shdr shdr;
+
+ while ((scn = elf_nextscn(elf, scn)) != NULL) {
+ Elf_Data *data;
+ size_t nsyms;
+
+ if (!gelf_getshdr(scn, &shdr))
+ continue;
+ if (shdr.sh_type != SHT_SYMTAB || !shdr.sh_entsize)
+ continue;
+
+ data = elf_getdata(scn, NULL);
+ if (!data)
+ continue;
+
+ nsyms = shdr.sh_size / shdr.sh_entsize;
+ for (size_t i = 0; i < nsyms; i++) {
+ GElf_Sym sym;
+ unsigned long long raw;
+
+ if (!gelf_getsym(data, i, &sym))
+ continue;
+ if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+ continue;
+ if (sym.st_value < text_addr)
+ continue;
+ if (text_end_addr && sym.st_value >= text_end_addr)
+ continue;
+
+ raw = sym.st_value - text_addr;
+ if (raw > UINT_MAX)
+ continue;
+
+ if (num_sym_starts >= sym_starts_capacity) {
+ sym_starts_capacity = sym_starts_capacity ?
+ sym_starts_capacity * 2 : 16384;
+ sym_starts = xrealloc(sym_starts,
+ sym_starts_capacity *
+ sizeof(*sym_starts));
+ }
+ sym_starts[num_sym_starts].offset = (unsigned int)raw;
+ sym_starts[num_sym_starts].size =
+ sym.st_size > UINT_MAX ? UINT_MAX :
+ (unsigned int)sym.st_size;
+ num_sym_starts++;
+ }
+ }
+
+ if (num_sym_starts > 1) {
+ unsigned int j = 0;
+
+ qsort(sym_starts, num_sym_starts, sizeof(*sym_starts),
+ compare_sym_starts);
+ for (unsigned int i = 1; i < num_sym_starts; i++) {
+ if (sym_starts[i].offset == sym_starts[j].offset)
+ continue;
+ if (++j != i)
+ sym_starts[j] = sym_starts[i];
+ }
+ num_sym_starts = j + 1;
+ }
+}
+
+static void process_dwarf(Dwarf *dwarf, unsigned long long text_addr)
+{
+ Dwarf_Off off = 0, next_off;
+ size_t hdr_size;
+
+ while (dwarf_nextcu(dwarf, off, &next_off, &hdr_size,
+ NULL, NULL, NULL) == 0) {
+ Dwarf_Die cudie;
+ Dwarf_Lines *lines;
+ size_t nlines;
+ Dwarf_Attribute attr;
+ const char *comp_dir = NULL;
+
+ if (!dwarf_offdie(dwarf, off + hdr_size, &cudie))
+ goto next;
+
+ if (dwarf_attr(&cudie, DW_AT_comp_dir, &attr))
+ comp_dir = dwarf_formstring(&attr);
+
+ if (dwarf_getsrclines(&cudie, &lines, &nlines) != 0)
+ goto next;
+
+ for (size_t i = 0; i < nlines; i++) {
+ Dwarf_Line *line = dwarf_onesrcline(lines, i);
+ Dwarf_Addr addr;
+ const char *src;
+ const char *rel;
+ unsigned int file_id, loffset;
+ bool endseq = false;
+ int lineno;
+
+ if (!line)
+ continue;
+
+ if (dwarf_lineaddr(line, &addr) != 0)
+ continue;
+
+ /*
+ * An end_sequence row marks the first address NOT
+ * covered by this sequence; libdw repeats the previous
+ * line number on it, so keeping it as an entry would
+ * extend a function's annotation past its own end.
+ * Record the boundary instead -- deduplicate() needs
+ * it to tell "this row still covers the next symbol"
+ * from "coverage stopped here".
+ */
+ if (dwarf_lineendsequence(line, &endseq) == 0 &&
endseq) {
+ record_seq_end(addr, text_addr);
+ continue;
+ }
+
+ if (dwarf_lineno(line, &lineno) != 0)
+ continue;
+ if (lineno == 0)
+ continue;
+
+ src = dwarf_linesrc(line, NULL, NULL);
+ if (!src)
+ continue;
+
+ if (addr < text_addr)
+ continue;
+ /*
+ * Skip addresses past _etext. Sections after .rodata
+ * shift when the real lineinfo replaces the empty stub
+ * during the multi-pass vmlinux link, so any address
+ * we'd capture there would be stale by the time the
+ * final kernel runs.
+ */
+ if (text_end_addr && addr >= text_end_addr)
+ continue;
+
+ {
+ unsigned long long raw_offset = addr -
text_addr;
+
+ if (raw_offset > UINT_MAX) {
+ skipped_overflow++;
+ continue;
+ }
+ loffset = (unsigned int)raw_offset;
+ }
+
+ rel = make_relative(src, comp_dir);
+ file_id = find_or_add_file(rel);
+
+ add_entry(loffset, file_id, (unsigned int)lineno);
+ }
+next:
+ off = next_off;
+ }
+}
+
+/* True if some line-program sequence ends in (@lo, @hi]. */
+static bool seq_end_between(unsigned int lo, unsigned int hi)
+{
+ unsigned int low = 0, high = num_seq_ends;
+
+ /* First index whose value exceeds @lo. */
+ while (low < high) {
+ unsigned int mid = low + (high - low) / 2;
+
+ if (seq_ends[mid] <= lo)
+ low = mid + 1;
+ else
+ high = mid;
+ }
+
+ return low < num_seq_ends && seq_ends[low] <= hi;
+}
+
+/*
+ * Give every function an entry at its own first byte.
+ *
+ * Compilers routinely emit no line row at a symbol's start: .cold
+ * fragments in particular are covered by a row belonging to the function
+ * they were split out of. That used to resolve fine, but the kernel now
+ * refuses any entry below the resolved symbol's start, so those frames
+ * would print unannotated. Copy the covering row down to the symbol
+ * start instead.
+ *
+ * Two things have to hold before that is honest:
+ *
+ * - the covering row's sequence must not have ended in between, or it
+ * describes code that stopped before this symbol. This is what keeps
+ * the __SCT__* static-call trampolines unannotated.
+ *
+ * - the line program must place at least one row inside the symbol, so
+ * we know it describes this symbol's code at all. This is what keeps
+ * the __pfx_* padding stubs unannotated: they are pure alignment
+ * padding, and no compiler ever emits a row inside one.
+ *
+ * Symbols failing either test keep no annotation, which is the correct
+ * answer for hand-written assembly.
+ */
+static void synthesize_symbol_starts(void)
+{
+ unsigned int base_entries = num_entries;
+ unsigned int cursor = 0;
+
+ if (!base_entries || !num_sym_starts)
+ return;
+
+ sort_unique(seq_ends, &num_seq_ends);
+
+ for (unsigned int i = 0; i < num_sym_starts; i++) {
+ unsigned int start = sym_starts[i].offset;
+ unsigned int end = start + sym_starts[i].size;
+
+ while (cursor + 1 < base_entries &&
+ entries[cursor + 1].offset <= start)
+ cursor++;
+
+ if (entries[cursor].offset > start)
+ continue; /* nothing covers this symbol */
+ if (entries[cursor].offset == start)
+ continue; /* already has its own entry */
+ if (seq_end_between(entries[cursor].offset, start))
+ continue; /* coverage stopped before here */
+
+ /* Overflow, or no row inside [start, end): not our code. */
+ if (end <= start)
+ continue;
+ if (cursor + 1 >= base_entries ||
+ entries[cursor + 1].offset >= end)
+ continue;
+
+ add_entry(start, entries[cursor].file_id, entries[cursor].line);
+ }
+}
+
+static void deduplicate(void)
+{
+ unsigned int sym_cursor = 0;
+ unsigned int i, j;
+
+ if (num_entries < 2)
+ return;
+
+ /* Sort by offset, then file_id, then line for stability */
+ qsort(entries, num_entries, sizeof(*entries), compare_entries);
+
+ synthesize_symbol_starts();
+ qsort(entries, num_entries, sizeof(*entries), compare_entries);
+
+ /*
+ * Remove duplicate entries:
+ * - Same offset: keep first (deterministic from stable sort keys)
+ * - Same file:line as previous kept entry: redundant for binary
+ * search -- any address between them resolves to the earlier one
+ *
+ * Entries sitting on a symbol start are exempt from the second rule:
+ * they are the only thing standing between that symbol and the
+ * kernel's boundary check.
+ */
+ j = 0;
+ for (i = 1; i < num_entries; i++) {
+ bool at_symbol_start;
+
+ if (entries[i].offset == entries[j].offset)
+ continue;
+
+ while (sym_cursor < num_sym_starts &&
+ sym_starts[sym_cursor].offset < entries[i].offset)
+ sym_cursor++;
+ at_symbol_start = sym_cursor < num_sym_starts &&
+ sym_starts[sym_cursor].offset ==
entries[i].offset;
+
+ if (!at_symbol_start &&
+ entries[i].file_id == entries[j].file_id &&
+ entries[i].line == entries[j].line)
+ continue;
+
+ j++;
+ if (j != i)
+ entries[j] = entries[i];
+ }
+ num_entries = j + 1;
+}
+
+static void compute_file_offsets(void)
+{
+ unsigned int offset = 0;
+
+ for (unsigned int i = 0; i < num_files; i++) {
+ files[i]->str_offset = offset;
+ offset += strlen(files[i]->name) + 1;
+ }
+}
+
+static void print_escaped_asciz(const char *s)
+{
+ printf("\t.asciz \"");
+ for (; *s; s++) {
+ if (*s == '"' || *s == '\\')
+ putchar('\\');
+ putchar(*s);
+ }
+ printf("\"\n");
+}
+
+static void output_assembly(void)
+{
+ printf("/* SPDX-License-Identifier: GPL-2.0 */\n");
+ printf("/*\n");
+ printf(" * Automatically generated by scripts/gen_lineinfo\n");
+ printf(" * Do not edit.\n");
+ printf(" */\n\n");
+
+ printf("\t.section .rodata, \"a\"\n\n");
+
+ /* Number of entries */
+ printf("\t.globl lineinfo_num_entries\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_num_entries:\n");
+ printf("\t.long %u\n\n", num_entries);
+
+ /* Number of files */
+ printf("\t.globl lineinfo_num_files\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_num_files:\n");
+ printf("\t.long %u\n\n", num_files);
+
+ /* Sorted address offsets from _text */
+ printf("\t.globl lineinfo_addrs\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_addrs:\n");
+ for (unsigned int i = 0; i < num_entries; i++)
+ printf("\t.long 0x%x\n", entries[i].offset);
+ printf("\n");
+
+ /* File IDs, parallel to addrs (u16 -- supports up to 65535 files) */
+ printf("\t.globl lineinfo_file_ids\n");
+ printf("\t.balign 2\n");
+ printf("lineinfo_file_ids:\n");
+ for (unsigned int i = 0; i < num_entries; i++)
+ printf("\t.short %u\n", entries[i].file_id);
+ printf("\n");
+
+ /* Line numbers, parallel to addrs */
+ printf("\t.globl lineinfo_lines\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_lines:\n");
+ for (unsigned int i = 0; i < num_entries; i++)
+ printf("\t.long %u\n", entries[i].line);
+ printf("\n");
+
+ /* File string offset table */
+ printf("\t.globl lineinfo_file_offsets\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_file_offsets:\n");
+ for (unsigned int i = 0; i < num_files; i++)
+ printf("\t.long %u\n", files[i]->str_offset);
+ printf("\n");
+
+ /* Filenames size */
+ {
+ unsigned int fsize = 0;
+
+ for (unsigned int i = 0; i < num_files; i++)
+ fsize += strlen(files[i]->name) + 1;
+ printf("\t.globl lineinfo_filenames_size\n");
+ printf("\t.balign 4\n");
+ printf("lineinfo_filenames_size:\n");
+ printf("\t.long %u\n\n", fsize);
+ }
+
+ /* Concatenated NUL-terminated filenames */
+ printf("\t.globl lineinfo_filenames\n");
+ printf("lineinfo_filenames:\n");
+ for (unsigned int i = 0; i < num_files; i++)
+ print_escaped_asciz(files[i]->name);
+ printf("\n");
+}
+
+int main(int argc, char *argv[])
+{
+ const char *kbuild_verbose = getenv("KBUILD_VERBOSE");
+ unsigned long long text_addr;
+ Dwarf *dwarf;
+ Elf *elf;
+ int fd;
+
+ if (kbuild_verbose && strchr(kbuild_verbose, '1'))
+ verbose = true;
+
+ while (argc > 2 && (!strcmp(argv[1], "-v") ||
+ !strcmp(argv[1], "--verbose"))) {
+ verbose = true;
+ memmove(&argv[1], &argv[2], (argc - 2) * sizeof(char *));
+ argc--;
+ }
+
+ if (argc != 2) {
+ fprintf(stderr, "Usage: %s [-v] <vmlinux>\n", argv[0]);
+ return 1;
+ }
+
+ init_path_roots();
+
+ fd = open(argv[1], O_RDONLY);
+ if (fd < 0)
+ error("cannot open %s: %s", argv[1], strerror(errno));
+
+ elf_version(EV_CURRENT);
+ elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+ if (!elf)
+ error("elf_begin failed: %s", elf_errmsg(elf_errno()));
+
+ text_addr = find_text_addr(elf);
+ text_end_addr = find_text_end_addr(elf);
+ collect_symbol_starts(elf, text_addr);
+
+ dwarf = dwarf_begin_elf(elf, DWARF_C_READ, NULL);
+ if (!dwarf)
+ error("dwarf_begin_elf failed: %s\n"
+ LINEINFO_PREFIX "error: is %s built with
CONFIG_DEBUG_INFO?",
+ dwarf_errmsg(dwarf_errno()), argv[1]);
+
+ process_dwarf(dwarf, text_addr);
+
+ if (skipped_overflow)
+ warn("%u entries skipped (offset > 4 GiB from _text)",
+ skipped_overflow);
+
+ deduplicate();
+ compute_file_offsets();
+
+ verbose_msg("%u entries, %u files", num_entries, num_files);
+
+ output_assembly();
+
+ dwarf_end(dwarf);
+ elf_end(elf);
+ close(fd);
+
+ /* Cleanup */
+ free(entries);
+ free(sym_starts);
+ free(seq_ends);
+ for (unsigned int i = 0; i < num_files; i++)
+ free(files[i]);
+ free(files);
+
+ return 0;
+}
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 37d5c095ad22..e11f101b743b 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -90,6 +90,17 @@ static bool is_ignored_symbol(const char *name, char type)
return true;
}
+ /*
+ * The generated lineinfo tables (scripts/gen_lineinfo, stubbed by
+ * scripts/empty_lineinfo.S) are read-only data whose size and
+ * addresses change between kallsyms passes. Match them by prefix so
+ * the set cannot drift as the table layout evolves. Text symbols are
+ * exempt, so lib/tests/lineinfo_kunit.c's lineinfo_target_*() stay
+ * resolvable -- the test looks them up by name.
+ */
+ if (toupper(type) != 'T' && !strncmp(name, "lineinfo_", 9))
+ return true;
+
return false;
}
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index f99e196abeea..39ca44fbb259 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -103,7 +103,7 @@ vmlinux_link()
${ld} ${ldflags} -o ${output} \
${wl}--whole-archive ${objs} ${wl}--no-whole-archive \
${wl}--start-group ${libs} ${wl}--end-group \
- ${kallsymso} ${btf_vmlinux_bin_o} ${arch_vmlinux_o} ${ldlibs}
+ ${kallsymso} ${lineinfo_o} ${btf_vmlinux_bin_o}
${arch_vmlinux_o} ${ldlibs}
}
# Create ${2}.o file with all symbols from the ${1} object file
@@ -129,6 +129,26 @@ kallsyms()
kallsymso=${2}.o
}
+# Generate lineinfo tables from DWARF debug info in a temporary vmlinux.
+# ${1} - temporary vmlinux with debug info
+# Output: sets lineinfo_o to the generated .o file
+gen_lineinfo()
+{
+ info LINEINFO .tmp_lineinfo.S
+ if ! scripts/gen_lineinfo "${1}" > .tmp_lineinfo.S; then
+ echo >&2 "Failed to generate lineinfo from ${1}"
+ echo >&2 "Try to disable CONFIG_KALLSYMS_LINEINFO"
+ exit 1
+ fi
+
+ info AS .tmp_lineinfo.o
+ ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
+ ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
+ -c -o .tmp_lineinfo.o .tmp_lineinfo.S
+
+ lineinfo_o=.tmp_lineinfo.o
+}
+
# Perform kallsyms for the given temporary vmlinux.
sysmap_and_kallsyms()
{
@@ -155,6 +175,7 @@ sorttable()
cleanup()
{
rm -f .btf.*
+ rm -f .tmp_lineinfo.*
rm -f .tmp_vmlinux.nm-sort
rm -f System.map
rm -f vmlinux
@@ -183,6 +204,7 @@ fi
btf_vmlinux_bin_o=
btfids_vmlinux=
kallsymso=
+lineinfo_o=
strip_debug=
generate_map=
@@ -198,10 +220,21 @@ if is_enabled CONFIG_KALLSYMS; then
kallsyms .tmp_vmlinux0.syms .tmp_vmlinux0.kallsyms
fi
+if is_enabled CONFIG_KALLSYMS_LINEINFO; then
+ # Assemble an empty lineinfo stub for the initial link.
+ # The real lineinfo is generated from .tmp_vmlinux1 by gen_lineinfo.
+ ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
+ ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
+ -c -o .tmp_lineinfo.o "${srctree}/scripts/empty_lineinfo.S"
+ lineinfo_o=.tmp_lineinfo.o
+fi
+
if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
- # The kallsyms linking does not need debug symbols, but the BTF does.
- if ! is_enabled CONFIG_DEBUG_INFO_BTF; then
+ # The kallsyms linking does not need debug symbols, but BTF and
+ # lineinfo generation do.
+ if ! is_enabled CONFIG_DEBUG_INFO_BTF &&
+ ! is_enabled CONFIG_KALLSYMS_LINEINFO; then
strip_debug=1
fi
@@ -219,6 +252,10 @@ if is_enabled CONFIG_DEBUG_INFO_BTF; then
btfids_vmlinux=.tmp_vmlinux1.BTF_ids
fi
+if is_enabled CONFIG_KALLSYMS_LINEINFO; then
+ gen_lineinfo .tmp_vmlinux1
+fi
+
if is_enabled CONFIG_KALLSYMS; then
# kallsyms support
--
2.53.0
