1 files changed, 90 insertions, 30 deletions
diff --git a/scripts/mksysmap b/scripts/mksysmap
index a35acc0d0b82..57ff5656d566 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -4,41 +4,101 @@
 # tools to retrieve the actual addresses of symbols in the kernel.
 #
 # Usage
-# mksysmap vmlinux System.map
+# mksysmap vmlinux System.map [exclude]
 
 
 #####
 # Generate System.map (actual filename passed as second argument)
-
-# $NM produces the following output:
-# f0081e80 T alloc_vfsmnt
-
-#   The second row specify the type of the symbol:
-#   A = Absolute
-#   B = Uninitialised data (.bss)
-#   C = Common symbol
-#   D = Initialised data
-#   G = Initialised data for small objects
-#   I = Indirect reference to another symbol
-#   N = Debugging symbol
-#   R = Read only
-#   S = Uninitialised data for small objects
-#   T = Text code symbol
-#   U = Undefined symbol
-#   V = Weak symbol
-#   W = Weak symbol
-#   Corresponding small letters are local symbols
-
-# For System.map filter away:
-#   a - local absolute symbols
-#   U - undefined global symbols
-#   N - debugging symbols
-#   w - local weak symbols
+# The following refers to the symbol type as per nm(1).
 
 # readprofile starts reading symbols when _stext is found, and
 # continue until it finds a symbol which is not either of 'T', 't',
-# 'W' or 'w'. __crc_ are 'A' and placed in the middle
-# so we just ignore them to let readprofile continue to work.
-# (At least sparc64 has __crc_ in the middle).
+# 'W' or 'w'.
+#
+
+${NM} -n ${1} | sed >${2} -e "
+# ---------------------------------------------------------------------------
+# Ignored symbol types
+#
+
+# a: local absolute symbols
+# N: debugging symbols
+# U: undefined global symbols
+# w: local weak symbols
+/ [aNUw] /d
+
+# ---------------------------------------------------------------------------
+# Ignored prefixes
+#  (do not forget a space before each pattern)
+
+# local symbols for ARM, MIPS, etc.
+/ \\$/d
+
+# local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc.
+/ \.L/d
+
+# arm64 EFI stub namespace
+/ __efistub_/d
+
+# arm64 local symbols in PIE namespace
+/ __pi_\\$/d
+/ __pi_\.L/d
+
+# arm64 local symbols in non-VHE KVM namespace
+/ __kvm_nvhe_\\$/d
+/ __kvm_nvhe_\.L/d
+
+# lld arm/aarch64/mips thunks
+/ __[[:alnum:]]*Thunk_/d
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( .L\)' > $2
+# CFI type identifiers
+/ __kcfi_typeid_/d
+/ __kvm_nvhe___kcfi_typeid_/d
+/ __pi___kcfi_typeid_/d
+
+# CRC from modversions
+/ __crc_/d
+
+# EXPORT_SYMBOL (symbol name)
+/ __kstrtab_/d
+
+# EXPORT_SYMBOL (namespace)
+/ __kstrtabns_/d
+
+# ---------------------------------------------------------------------------
+# Ignored suffixes
+#  (do not forget '$' after each pattern)
+
+# arm
+/_from_arm$/d
+/_from_thumb$/d
+/_veneer$/d
+
+# ---------------------------------------------------------------------------
+# Ignored symbols (exact match)
+#  (do not forget a space before and '$' after each pattern)
+
+# for LoongArch?
+/ L0$/d
+
+# ppc
+/ _SDA_BASE_$/d
+/ _SDA2_BASE_$/d
+
+# ---------------------------------------------------------------------------
+# Ignored patterns
+#  (symbols that contain the pattern are ignored)
+
+# ppc stub
+/\.long_branch\./d
+/\.plt_branch\./d
+
+# ---------------------------------------------------------------------------
+# Ignored kallsyms symbols
+#
+# If the 3rd parameter exists, symbols from it will be omitted from the output.
+# This makes kallsyms have the identical symbol lists in the step 1 and 2.
+# Without this, the step2 would get new symbols generated by scripts/kallsyms.c
+# when CONFIG_KALLSYMS_ALL is enabled. That might require one more pass.
+$(if [ $# -ge 3 ]; then ${NM} ${3} | sed -n '/ U /!s:.* \([^ ]*\)$:/ \1$/d:p'; fi)
+"