From 0ad2507d5d93f39619fc42372c347d6006b64319 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 16 Feb 2025 14:02:44 -0800
Subject: [PATCH 01/16] Linux 6.14-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 272db408be5c..96407c1d6be1 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
2.51.0


From a3e8fe814ad15c16735cdf394454a8bd96eb4d56 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:33 -0500
Subject: [PATCH 02/16] x86/build: Raise the minimum GCC version to 8.1

Stack protector support on 64-bit currently requires that the percpu
section is linked at absolute address 0, because older compilers fixed
the location of the canary value relative to the GS segment base.

GCC 8.1 introduced options to change where the canary value is located,
allowing it to be configured as a standard per-CPU variable.  This has
already been done for 32-bit.  Doing the same for 64-bit will enable
removing the code needed to support zero-based percpu.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-2-brgerst@gmail.com
---
 scripts/min-tool-version.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 91c91201212c..06c4e410ecab 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -19,6 +19,8 @@ binutils)
 gcc)
 	if [ "$ARCH" = parisc64 ]; then
 		echo 12.0.0
+	elif [ "$SRCARCH" = x86 ]; then
+		echo 8.1.0
 	else
 		echo 5.1.0
 	fi
-- 
2.51.0


From 0ee2689b9374d6fd5f43b703713a532278654749 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:34 -0500
Subject: [PATCH 03/16] x86/stackprotector: Remove stack protector test scripts

With GCC 8.1 now the minimum supported compiler for x86, these scripts
are no longer needed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-3-brgerst@gmail.com
---
 arch/x86/Kconfig                          | 11 +----------
 scripts/gcc-x86_32-has-stack-protector.sh |  8 --------
 scripts/gcc-x86_64-has-stack-protector.sh |  4 ----
 3 files changed, 1 insertion(+), 22 deletions(-)
 delete mode 100755 scripts/gcc-x86_32-has-stack-protector.sh
 delete mode 100755 scripts/gcc-x86_64-has-stack-protector.sh

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118..6595b35dd52d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -285,7 +285,7 @@ config X86
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
-	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
+	select HAVE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
@@ -426,15 +426,6 @@ config PGTABLE_LEVELS
 	default 3 if X86_PAE
 	default 2
 
-config CC_HAS_SANE_STACKPROTECTOR
-	bool
-	default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
-	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC) $(CLANG_FLAGS))
-	help
-	  We have to make sure stack protector is unconditionally disabled if
-	  the compiler produces broken code or if it does not let us control
-	  the segment on 32-bit kernels.
-
 menu "Processor type and features"
 
 config SMP
diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
deleted file mode 100755
index 9459ca4f0f11..000000000000
--- a/scripts/gcc-x86_32-has-stack-protector.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# This requires GCC 8.1 or better.  Specifically, we require
-# -mstack-protector-guard-reg, added by
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
deleted file mode 100755
index f680bb01aeeb..000000000000
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
-- 
2.51.0


From a9a76b38aaf577887103e3ebb41d70e6aa5a4b19 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:35 -0500
Subject: [PATCH 04/16] x86/boot: Disable stack protector for early boot code

On 64-bit, this will prevent crashes when the canary access is changed
from %gs:40 to %gs:__stack_chk_guard(%rip).  RIP-relative addresses from
the identity-mapped early boot code will target the wrong address with
zero-based percpu.  KASLR could then shift that address to an unmapped
page causing a crash on boot.

This early boot code runs well before user-space is active and does not
need stack protector enabled.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-4-brgerst@gmail.com
---
 arch/x86/kernel/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b43eb7e384eb..84cfa179802c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,8 @@ KCOV_INSTRUMENT_unwind_orc.o				:= n
 KCOV_INSTRUMENT_unwind_frame.o				:= n
 KCOV_INSTRUMENT_unwind_guess.o				:= n
 
+CFLAGS_head32.o := -fno-stack-protector
+CFLAGS_head64.o := -fno-stack-protector
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
 
 obj-y			+= head_$(BITS).o
-- 
2.51.0


From f58b63857ae38b4484185b799a2759274b930c92 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:36 -0500
Subject: [PATCH 05/16] x86/pvh: Use fixed_percpu_data for early boot GSBASE

Instead of having a private area for the stack canary, use
fixed_percpu_data for GSBASE like the native kernel.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-5-brgerst@gmail.com
---
 arch/x86/platform/pvh/head.S | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 4733a5f467b8..723f181b222a 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -173,10 +173,15 @@ SYM_CODE_START(pvh_start_xen)
 1:
 	UNWIND_HINT_END_OF_STACK
 
-	/* Set base address in stack canary descriptor. */
-	mov $MSR_GS_BASE,%ecx
-	leal canary(%rip), %eax
-	xor %edx, %edx
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
+	movl $MSR_GS_BASE,%ecx
+	leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+	movq %edx, %eax
+	shrq $32, %rdx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
@@ -238,8 +243,6 @@ SYM_DATA_START_LOCAL(gdt_start)
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
-SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
-
 SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
-- 
2.51.0


From cb7927fda002ca49ae62e2782c1692acc7b80c67 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:37 -0500
Subject: [PATCH 06/16] x86/relocs: Handle R_X86_64_REX_GOTPCRELX relocations

Clang may produce R_X86_64_REX_GOTPCRELX relocations when redefining the
stack protector location.  Treat them as another type of PC-relative
relocation.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-6-brgerst@gmail.com
---
 arch/x86/tools/relocs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e937be979ec8..92a1e503305e 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -32,6 +32,11 @@ static struct relocs		relocs32;
 static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
 #else
 # define FMT PRIu32
 #endif
@@ -227,6 +232,7 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_X86_64_PC16),
 		REL_TYPE(R_X86_64_8),
 		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
 #else
 		REL_TYPE(R_386_NONE),
 		REL_TYPE(R_386_32),
@@ -861,6 +867,7 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 
 	case R_X86_64_PC32:
 	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
 		/*
 		 * PC relative relocations don't need to be adjusted unless
 		 * referencing a percpu symbol.
-- 
2.51.0


From 78c4374ef8b842c6abf195d6f963853c7ec464d2 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 23 Jan 2025 14:07:38 -0500
Subject: [PATCH 07/16] x86/module: Deal with GOT based stack cookie load on
 Clang < 17

Clang versions before 17 will not honour -fdirect-access-external-data
for the load of the stack cookie emitted into each function's prologue
and epilogue.

This is not an issue for the core kernel, as the linker will relax these
loads into LEA instructions that take the address of __stack_chk_guard
directly. For modules, however, we need to work around this, by dealing
with R_X86_64_REX_GOTPCRELX relocations that refer to __stack_chk_guard.

In this case, given that this is a GOT load, the reference should not
refer to __stack_chk_guard directly, but to a memory location that holds
its address. So take the address of __stack_chk_guard into a static
variable, and fix up the relocations to refer to that.

[ mingo: Fix broken R_X86_64_GOTPCRELX definition. ]

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-7-brgerst@gmail.com
---
 arch/x86/include/asm/elf.h |  5 +++--
 arch/x86/kernel/module.c   | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f..128602612eca 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
 #define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
 #define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
 #define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX	41
+#define R_X86_64_REX_GOTPCRELX	42
 #define R_X86_64_32		10	/* Direct 32 bit zero extended */
 #define R_X86_64_32S		11	/* Direct 32 bit sign extended */
 #define R_X86_64_16		12	/* Direct 16 bit zero extended */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c00..a286f32c5503 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 #include <linux/memory.h>
+#include <linux/stackprotector.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -130,6 +131,20 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 				goto overflow;
 			size = 4;
 			break;
+#if defined(CONFIG_STACKPROTECTOR) && \
+    defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+		case R_X86_64_REX_GOTPCRELX: {
+			static unsigned long __percpu *const addr = &__stack_chk_guard;
+
+			if (sym->st_value != (u64)addr) {
+				pr_err("%s: Unsupported GOTPCREL relocation\n", me->name);
+				return -ENOEXEC;
+			}
+
+			val = (u64)&addr + rel[i].r_addend;
+			fallthrough;
+		}
+#endif
 		case R_X86_64_PC32:
 		case R_X86_64_PLT32:
 			val -= (u64)loc;
-- 
2.51.0


From 80d47defddc000271502057ebd7efa4fd6481542 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:39 -0500
Subject: [PATCH 08/16] x86/stackprotector/64: Convert to normal per-CPU
 variable

Older versions of GCC fixed the location of the stack protector canary
at %gs:40.  This constraint forced the percpu section to be linked at
absolute address 0 so that the canary could be the first data object in
the percpu section.  Supporting the zero-based percpu section requires
additional code to handle relocations for RIP-relative references to
percpu data, extra complexity to kallsyms, and workarounds for linker
bugs due to the use of absolute symbols.

GCC 8.1 supports redefining where the canary is located, allowing it to
become a normal percpu variable instead of at a fixed location.  This
removes the constraint that the percpu section must be zero-based.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-8-brgerst@gmail.com
---
 arch/x86/Makefile                     | 20 +++++++++------
 arch/x86/entry/entry.S                |  2 --
 arch/x86/entry/entry_64.S             |  2 +-
 arch/x86/include/asm/processor.h      | 16 ++----------
 arch/x86/include/asm/stackprotector.h | 36 ++++-----------------------
 arch/x86/kernel/asm-offsets_64.c      |  6 -----
 arch/x86/kernel/cpu/common.c          |  5 +---
 arch/x86/kernel/head_64.S             |  3 +--
 arch/x86/xen/xen-head.S               |  3 +--
 9 files changed, 23 insertions(+), 70 deletions(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b773b34768d..88a1705366f9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -140,14 +140,7 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-    ifeq ($(CONFIG_STACKPROTECTOR),y)
-        ifeq ($(CONFIG_SMP),y)
-            KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \
-                             -mstack-protector-guard-symbol=__ref_stack_chk_guard
-        else
-            KBUILD_CFLAGS += -mstack-protector-guard=global
-        endif
-    endif
+        percpu_seg := fs
 else
         BITS := 64
         UTS_MACHINE := x86_64
@@ -197,6 +190,17 @@ else
         KBUILD_CFLAGS += -mcmodel=kernel
         KBUILD_RUSTFLAGS += -Cno-redzone=y
         KBUILD_RUSTFLAGS += -Ccode-model=kernel
+
+        percpu_seg := gs
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR),y)
+    ifeq ($(CONFIG_SMP),y)
+	KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
+	KBUILD_CFLAGS += -mstack-protector-guard-symbol=__ref_stack_chk_guard
+    else
+	KBUILD_CFLAGS += -mstack-protector-guard=global
+    endif
 endif
 
 #
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9ecc..fe5344a249a1 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -52,7 +52,6 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
 
 THUNK warn_thunk_thunk, __warn_thunk
 
-#ifndef CONFIG_X86_64
 /*
  * Clang's implementation of TLS stack cookies requires the variable in
  * question to be a TLS variable. If the variable happens to be defined as an
@@ -66,4 +65,3 @@ THUNK warn_thunk_thunk, __warn_thunk
 #ifdef CONFIG_STACKPROTECTOR
 EXPORT_SYMBOL(__ref_stack_chk_guard);
 #endif
-#endif
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93c..33a955aa01d8 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -192,7 +192,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
+	movq	%rbx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 	/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90..a4687122951f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -422,16 +422,8 @@ struct irq_stack {
 
 #ifdef CONFIG_X86_64
 struct fixed_percpu_data {
-	/*
-	 * GCC hardcodes the stack canary as %gs:40.  Since the
-	 * irq_stack is the object at %gs:0, we reserve the bottom
-	 * 48 bytes of the irq stack for the canary.
-	 *
-	 * Once we are willing to require -mstack-protector-guard-symbol=
-	 * support for x86_64 stackprotector, we can get rid of this.
-	 */
 	char		gs_base[40];
-	unsigned long	stack_canary;
+	unsigned long	reserved;
 };
 
 DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
@@ -446,11 +438,7 @@ extern asmlinkage void entry_SYSCALL32_ignore(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
 void current_save_fsgs(void);
-#else	/* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif	/* !X86_64 */
+#endif	/* X86_64 */
 
 struct perf_event;
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f51..d43fb589fcf6 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
 /*
  * GCC stack protector support.
  *
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base.  On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary.  On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset.  On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function.  The pattern is called the stack canary
+ * and is a unique value for each task.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
 
 #include <linux/sched.h>
 
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary = get_random_canary();
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
 	current->stack_canary = canary;
-#ifdef CONFIG_X86_64
-	this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
 	this_cpu_write(__stack_chk_guard, canary);
-#endif
 }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 {
-#ifdef CONFIG_X86_64
-	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
 	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
 }
 
 #else	/* STACKPROTECTOR */
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index bb65371ea9df..590b6cd0eac0 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,11 +54,5 @@ int main(void)
 	BLANK();
 #undef ENTRY
 
-	BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
-	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
-	BLANK();
-#endif
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2..b71178f0ed6c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2089,8 +2089,7 @@ void syscall_init(void)
 	if (!cpu_feature_enabled(X86_FEATURE_FRED))
 		idt_syscall_init();
 }
-
-#else	/* CONFIG_X86_64 */
+#endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
 DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
@@ -2099,8 +2098,6 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * Clear all 6 debug registers:
  */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 31345e0ba006..c3d73c04603f 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -361,8 +361,7 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to fixed_percpu_data. If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	 * The base of %gs always points to fixed_percpu_data.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62..a31b057e641e 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -33,8 +33,7 @@ SYM_CODE_START(startup_xen)
 
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	 * The base of %gs always points to fixed_percpu_data.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
-- 
2.51.0


From 9d7de2aa8b41407bc96d89a80dc1fd637d389d42 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:40 -0500
Subject: [PATCH 09/16] x86/percpu/64: Use relative percpu offsets

The percpu section is currently linked at absolute address 0, because
older compilers hard-coded the stack protector canary value at a fixed
offset from the start of the GS segment.  Now that the canary is a
normal percpu variable, the percpu section does not need to be linked
at a specific address.

x86-64 will now calculate the percpu offsets as the delta between the
initial percpu address and the dynamically allocated memory, like other
architectures.  Note that GSBASE is limited to the canonical address
width (48 or 57 bits, sign-extended).  As long as the kernel text,
modules, and the dynamically allocated percpu memory are all in the
negative address space, the delta will not overflow this limit.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-9-brgerst@gmail.com
---
 arch/x86/include/asm/processor.h |  6 +++++-
 arch/x86/kernel/head_64.S        | 19 +++++++++----------
 arch/x86/kernel/setup_percpu.c   | 12 ++----------
 arch/x86/kernel/vmlinux.lds.S    | 29 +----------------------------
 arch/x86/platform/pvh/head.S     |  5 ++---
 arch/x86/tools/relocs.c          | 10 +++-------
 arch/x86/xen/xen-head.S          |  9 ++++-----
 init/Kconfig                     |  2 +-
 8 files changed, 27 insertions(+), 65 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4687122951f..b8fee88dac3d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -431,7 +431,11 @@ DECLARE_INIT_PER_CPU(fixed_percpu_data);
 
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+	return per_cpu_offset(cpu);
+#else
+	return 0;
+#endif
 }
 
 extern asmlinkage void entry_SYSCALL32_ignore(void);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index c3d73c04603f..2843b0a56198 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -61,11 +61,14 @@ SYM_CODE_START_NOALIGN(startup_64)
 	/* Set up the stack for verify_cpu() */
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Setup GSBASE to allow stack canary access for C code */
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
 	movl	$MSR_GS_BASE, %ecx
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movl	%edx, %eax
-	shrq	$32,  %rdx
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	call	startup_64_setup_gdt_idt
@@ -359,16 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
 	movl	%edx, %eax
 	shrq	$32, %rdx
 	wrmsr
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7..1e7be9409aa2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,10 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
-
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
-	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
 EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0deb4887d6e9..8a598515239a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -112,12 +112,6 @@ ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(6);        /* RW_ */
-#endif
-	init PT_LOAD FLAGS(7);          /* RWE */
-#endif
 	note PT_NOTE FLAGS(0);          /* ___ */
 }
 
@@ -216,21 +210,7 @@ SECTIONS
 		__init_begin = .; /* paired with __init_end */
 	}
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
-	/*
-	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-	 * output PHDR, so the next output section - .init.text - should
-	 * start another segment - init.
-	 */
-	PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
-	ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
-	       "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
 	INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
-	:init
-#endif
 
 	/*
 	 * Section for code used exclusively before alternatives are run. All
@@ -347,9 +327,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
 	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
@@ -497,16 +475,11 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
  * Per-cpu symbols which need to be offset from __per_cpu_load
  * for the boot processor.
  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
 INIT_PER_CPU(gdt_page);
 INIT_PER_CPU(fixed_percpu_data);
 INIT_PER_CPU(irq_stack_backing_store);
 
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
-           "fixed_percpu_data is not at start of per-cpu area");
-#endif
-
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
 #endif
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 723f181b222a..cfa18ec7d55f 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -179,9 +179,8 @@ SYM_CODE_START(pvh_start_xen)
 	 * the per-CPU areas are set up.
 	 */
 	movl $MSR_GS_BASE,%ecx
-	leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movq %edx, %eax
-	shrq $32, %rdx
+	xorl %eax, %eax
+	xorl %edx, %edx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 92a1e503305e..3cb3b30b6706 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -835,12 +835,7 @@ static void percpu_init(void)
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
-	int shndx = sym_index(sym);
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
+	return 0;
 }
 
 
@@ -1062,7 +1057,8 @@ static int cmp_relocs(const void *va, const void *vb)
 
 static void sort_relocs(struct relocs *r)
 {
-	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
 }
 
 static int write32(uint32_t v, FILE *f)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index a31b057e641e..5ccb4c54e241 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,15 +31,14 @@ SYM_CODE_START(startup_xen)
 
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
-	cdq
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi
diff --git a/init/Kconfig b/init/Kconfig
index d0d021b3fa3b..b5d9c0fa69f6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1872,7 +1872,7 @@ config KALLSYMS_ALL
 config KALLSYMS_ABSOLUTE_PERCPU
 	bool
 	depends on KALLSYMS
-	default X86_64 && SMP
+	default n
 
 # end of the "standard kernel features (expert users)" menu
 
-- 
2.51.0


From b5c4f95351a097a635c1a7fc8d9efa18308491b5 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:41 -0500
Subject: [PATCH 10/16] x86/percpu/64: Remove fixed_percpu_data

Now that the stack protector canary value is a normal percpu variable,
fixed_percpu_data is unused and can be removed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-10-brgerst@gmail.com
---
 arch/x86/include/asm/processor.h | 8 --------
 arch/x86/kernel/cpu/common.c     | 4 ----
 arch/x86/kernel/vmlinux.lds.S    | 1 -
 arch/x86/tools/relocs.c          | 1 -
 4 files changed, 14 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b8fee88dac3d..b3d153730f63 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -421,14 +421,6 @@ struct irq_stack {
 } __aligned(IRQ_STACK_SIZE);
 
 #ifdef CONFIG_X86_64
-struct fixed_percpu_data {
-	char		gs_base[40];
-	unsigned long	reserved;
-};
-
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
-
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b71178f0ed6c..8b49b1338f76 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2023,10 +2023,6 @@ EXPORT_PER_CPU_SYMBOL(pcpu_hot);
 EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
-		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
-
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8a598515239a..93c2fa8a7522 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -477,7 +477,6 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(fixed_percpu_data);
 INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 3cb3b30b6706..b5e3695a0615 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -830,7 +830,6 @@ static void percpu_init(void)
  *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
- *	init_per_cpu__fixed_percpu_data
  *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-- 
2.51.0


From a8327be7b2aa067ff2b11551732d5bd8b49ef7d1 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:42 -0500
Subject: [PATCH 11/16] x86/boot/64: Remove inverse relocations

Inverse relocations were needed to offset the effects of relocation for
RIP-relative accesses to zero-based percpu data.  Now that the percpu
section is linked normally as part of the kernel image, they are no
longer needed.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-11-brgerst@gmail.com
---
 arch/x86/boot/compressed/misc.c |  14 +---
 arch/x86/tools/relocs.c         | 130 +-------------------------------
 2 files changed, 2 insertions(+), 142 deletions(-)

diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0d37420cad02..1cdcd4aaf395 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -235,7 +235,7 @@ static void handle_relocations(void *output, unsigned long output_len,
 
 	/*
 	 * Process relocations: 32 bit relocations first then 64 bit after.
-	 * Three sets of binary relocations are added to the end of the kernel
+	 * Two sets of binary relocations are added to the end of the kernel
 	 * before compression. Each relocation table entry is the kernel
 	 * address of the location which needs to be updated stored as a
 	 * 32-bit value which is sign extended to 64 bits.
@@ -245,8 +245,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 	 * kernel bits...
 	 * 0 - zero terminator for 64 bit relocations
 	 * 64 bit relocation repeated
-	 * 0 - zero terminator for inverse 32 bit relocations
-	 * 32 bit inverse relocation repeated
 	 * 0 - zero terminator for 32 bit relocations
 	 * 32 bit relocation repeated
 	 *
@@ -263,16 +261,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 		*(uint32_t *)ptr += delta;
 	}
 #ifdef CONFIG_X86_64
-	while (*--reloc) {
-		long extended = *reloc;
-		extended += map;
-
-		ptr = (unsigned long)extended;
-		if (ptr < min_addr || ptr > max_addr)
-			error("inverse 32-bit relocation outside of kernel!\n");
-
-		*(int32_t *)ptr -= delta;
-	}
 	for (reloc--; *reloc; reloc--) {
 		long extended = *reloc;
 		extended += map;
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b5e3695a0615..ae6962665b35 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,7 +29,6 @@ static struct relocs		relocs16;
 static struct relocs		relocs32;
 
 #if ELF_BITS == 64
-static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
 
@@ -91,7 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
 	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
@@ -290,34 +288,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 	return name;
 }
 
-static Elf_Sym *sym_lookup(const char *symname)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		struct section *sec = &secs[i];
-		long nsyms;
-		char *strtab;
-		Elf_Sym *symtab;
-		Elf_Sym *sym;
-
-		if (sec->shdr.sh_type != SHT_SYMTAB)
-			continue;
-
-		nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
-		symtab = sec->symtab;
-		strtab = sec->link->strtab;
-
-		for (sym = symtab; --nsyms >= 0; sym++) {
-			if (!sym->st_name)
-				continue;
-			if (strcmp(symname, strtab + sym->st_name) == 0)
-				return sym;
-		}
-	}
-	return 0;
-}
-
 #if BYTE_ORDER == LITTLE_ENDIAN
 # define le16_to_cpu(val)	(val)
 # define le32_to_cpu(val)	(val)
@@ -766,78 +736,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 	}
 }
 
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- *	Relocations that reference symbols in the per_cpu area do not
- *	need further relocation (since the value is an offset relative
- *	to the start of the per_cpu area that does not change).
- *
- *	Relocations that apply to the per_cpu area need to have their
- *	offset adjusted by by the value of __per_cpu_load to make them
- *	point to the correct place in the loaded image (because the
- *	virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		ElfW(Sym) *sym;
-
-		if (strcmp(sec_name(i), ".data..percpu"))
-			continue;
-
-		if (secs[i].shdr.sh_addr != 0)	/* non SMP kernel */
-			return;
-
-		sym = sym_lookup("__per_cpu_load");
-		if (!sym)
-			die("can't find __per_cpu_load\n");
-
-		per_cpu_shndx = i;
-		per_cpu_load_addr = sym->st_value;
-
-		return;
-	}
-}
-
 #if ELF_BITS == 64
 
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- *	__init_begin
- *	__per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- *	init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
-	return 0;
-}
-
-
 static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 		      const char *symname)
 {
@@ -848,12 +748,6 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	if (sym->st_shndx == SHN_UNDEF)
 		return 0;
 
-	/*
-	 * Adjust the offset if this reloc applies to the percpu section.
-	 */
-	if (sec->shdr.sh_info == per_cpu_shndx)
-		offset += per_cpu_load_addr;
-
 	switch (r_type) {
 	case R_X86_64_NONE:
 		/* NONE can be ignored. */
@@ -863,32 +757,21 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	case R_X86_64_PLT32:
 	case R_X86_64_REX_GOTPCRELX:
 		/*
-		 * PC relative relocations don't need to be adjusted unless
-		 * referencing a percpu symbol.
+		 * PC relative relocations don't need to be adjusted.
 		 *
 		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
-		if (is_percpu_sym(sym, symname))
-			add_reloc(&relocs32neg, offset);
 		break;
 
 	case R_X86_64_PC64:
 		/*
 		 * Only used by jump labels
 		 */
-		if (is_percpu_sym(sym, symname))
-			die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
 		break;
 
 	case R_X86_64_32:
 	case R_X86_64_32S:
 	case R_X86_64_64:
-		/*
-		 * References to the percpu area don't need to be adjusted.
-		 */
-		if (is_percpu_sym(sym, symname))
-			break;
-
 		if (shn_abs) {
 			/*
 			 * Whitelisted absolute symbols do not require
@@ -1101,7 +984,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
@@ -1133,13 +1015,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 		/* Now print each relocation */
 		for (i = 0; i < relocs64.count; i++)
 			write_reloc(relocs64.offset[i], stdout);
-
-		/* Print a stop */
-		write_reloc(0, stdout);
-
-		/* Now print each inverse 32-bit relocation */
-		for (i = 0; i < relocs32neg.count; i++)
-			write_reloc(relocs32neg.offset[i], stdout);
 #endif
 
 		/* Print a stop */
@@ -1192,9 +1067,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
 	read_symtabs(fp);
 	read_relocs(fp);
 
-	if (ELF_BITS == 64)
-		percpu_init();
-
 	if (show_absolute_syms) {
 		print_absolute_symbols();
 		return;
-- 
2.51.0


From 38a4968b3190f873a8a60e953287278eddf037f1 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:43 -0500
Subject: [PATCH 12/16] x86/percpu/64: Remove INIT_PER_CPU macros

Now that the load and link addresses of percpu variables are the same,
these macros are no longer necessary.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-12-brgerst@gmail.com
---
 arch/x86/include/asm/desc.h   |  1 -
 arch/x86/include/asm/percpu.h | 22 ----------------------
 arch/x86/kernel/head64.c      |  2 +-
 arch/x86/kernel/irq_64.c      |  1 -
 arch/x86/kernel/vmlinux.lds.S |  7 -------
 arch/x86/tools/relocs.c       |  1 -
 6 files changed, 1 insertion(+), 33 deletions(-)

diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea76..ec95fe44fa3a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999..1a76eb87c5d8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,12 +20,6 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var)  var
-#endif
-
 #else /* !__ASSEMBLY__: */
 
 #include <linux/build_bug.h>
@@ -97,22 +91,6 @@
 #define __percpu_arg(x)		__percpu_prefix "%" #x
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
-/*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(var) init_per_cpu_var(var)
-
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var)  init_per_cpu__##var
-#else
-# define init_per_cpu_var(var)  var
-#endif
-
 /*
  * For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though).
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 22c9ba305ac1..05f8b8acf784 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -567,7 +567,7 @@ void early_setup_idt(void)
  */
 void __head startup_64_setup_gdt_idt(void)
 {
-	struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
+	struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
 	void *handler = NULL;
 
 	struct desc_ptr startup_gdt_descr = {
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ade0043ce56e..56bdeecd8ee0 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -27,7 +27,6 @@
 #include <asm/apic.h>
 
 DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_VMAP_STACK
 /*
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 93c2fa8a7522..1769a7126224 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -471,13 +471,6 @@ SECTIONS
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 
 #ifdef CONFIG_X86_64
-/*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index ae6962665b35..5778bc498415 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -90,7 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"
-- 
2.51.0


From 95b0916118106054e1f3d5d7f8628ef3dc0b3c02 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:44 -0500
Subject: [PATCH 13/16] percpu: Remove PER_CPU_FIRST_SECTION

x86-64 was the last user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-13-brgerst@gmail.com
---
 include/asm-generic/vmlinux.lds.h |  1 -
 include/linux/percpu-defs.h       | 12 ------------
 2 files changed, 13 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 02a4adb4a999..a3c77a106565 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1062,7 +1062,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5b520fe86b60..40d34e032d5b 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
 #define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
 #else
 
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
 
 #endif
 
@@ -114,16 +112,6 @@
 #define DEFINE_PER_CPU(type, name)					\
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
-/*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
- */
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline
  * aligned under SMP conditions so that, whilst a particular instance of the
-- 
2.51.0


From e23cff6861781ac4e15de6c7bf2d2a0b79cb52ef Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:45 -0500
Subject: [PATCH 14/16] percpu: Remove PERCPU_VADDR()

x86-64 was the last user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-14-brgerst@gmail.com
---
 include/asm-generic/vmlinux.lds.h | 36 +------------------------------
 1 file changed, 1 insertion(+), 35 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a3c77a106565..e25a8aeee29c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1073,47 +1073,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__per_cpu_end = .;
 
 /**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
  * @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
  *
  * Macro which expands to output section for percpu area.
  *
  * @cacheline is used to align subsections to avoid false cacheline
  * sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address.  If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank.  Be warned that
- * output PHDR is sticky.  If @phdr is specified, the next output
- * section in the linker script will go there too.  @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	__per_cpu_load = .;						\
-	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
-		PERCPU_INPUT(cacheline)					\
-	} phdr								\
-	. = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area.  This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
  */
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
-- 
2.51.0


From 4b00c1160a13d8bf7297ebf49ec07a84e1f41132 Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:46 -0500
Subject: [PATCH 15/16] percpu: Remove __per_cpu_load

__per_cpu_load is now always equal to __per_cpu_start.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-15-brgerst@gmail.com
---
 include/asm-generic/sections.h    | 2 +-
 include/asm-generic/vmlinux.lds.h | 1 -
 mm/percpu.c                       | 4 ++--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9..0755bc39b0d8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index e25a8aeee29c..92fc06f7da74 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1084,7 +1084,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
diff --git a/mm/percpu.c b/mm/percpu.c
index ac61e3fc5f15..7b5835356d1e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3071,7 +3071,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 				continue;
 			}
 			/* copy and return the unused part */
-			memcpy(ptr, __per_cpu_load, ai->static_size);
+			memcpy(ptr, __per_cpu_start, ai->static_size);
 			pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
 		}
 	}
@@ -3240,7 +3240,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
-		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
+		memcpy((void *)unit_addr, __per_cpu_start, ai->static_size);
 	}
 
 	/* we're ready, commit */
-- 
2.51.0


From 01157ddc58dc2fe428ec17dd5a18cc13f134639f Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Thu, 23 Jan 2025 14:07:47 -0500
Subject: [PATCH 16/16] kallsyms: Remove KALLSYMS_ABSOLUTE_PERCPU

x86-64 was the only user.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250123190747.745588-16-brgerst@gmail.com
---
 init/Kconfig            |  5 ---
 kernel/kallsyms.c       | 12 ++-----
 scripts/kallsyms.c      | 72 +++++++----------------------------------
 scripts/link-vmlinux.sh |  4 ---
 4 files changed, 14 insertions(+), 79 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index b5d9c0fa69f6..a0ea04c17784 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1869,11 +1869,6 @@ config KALLSYMS_ALL
 
 	  Say N unless you really need all symbols, or kernel live patching.
 
-config KALLSYMS_ABSOLUTE_PERCPU
-	bool
-	depends on KALLSYMS
-	default 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 a9a0ca605d4a..4198f30aac3c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -148,16 +148,8 @@ static unsigned int get_symbol_offset(unsigned long pos)
 
 unsigned long kallsyms_sym_address(int idx)
 {
-	/* values are unsigned offsets if --absolute-percpu is not in effect */
-	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
-		return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
-
-	/* ...otherwise, positive offsets are absolute values */
-	if (kallsyms_offsets[idx] >= 0)
-		return kallsyms_offsets[idx];
-
-	/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
-	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+	/* values are unsigned offsets */
+	return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
 }
 
 static unsigned int get_symbol_seq(int index)
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 03852da3d249..4b0234e4b12f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,7 +5,7 @@
  * This software may be used and distributed according to the terms
  * of the GNU General Public License, incorporated herein by reference.
  *
- * Usage: kallsyms [--all-symbols] [--absolute-percpu]  in.map > out.S
+ * Usage: kallsyms [--all-symbols] in.map > out.S
  *
  *      Table compression uses all the unused char codes on the symbols and
  *  maps these to the most used substrings (tokens). For instance, it might
@@ -37,7 +37,6 @@ struct sym_entry {
 	unsigned long long addr;
 	unsigned int len;
 	unsigned int seq;
-	bool percpu_absolute;
 	unsigned char sym[];
 };
 
@@ -55,14 +54,9 @@ static struct addr_range text_ranges[] = {
 #define text_range_text     (&text_ranges[0])
 #define text_range_inittext (&text_ranges[1])
 
-static struct addr_range percpu_range = {
-	"__per_cpu_start", "__per_cpu_end", -1ULL, 0
-};
-
 static struct sym_entry **table;
 static unsigned int table_size, table_cnt;
 static int all_symbols;
-static int absolute_percpu;
 
 static int token_profit[0x10000];
 
@@ -73,7 +67,7 @@ static unsigned char best_table_len[256];
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] in.map > out.S\n");
 	exit(1);
 }
 
@@ -164,7 +158,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 		return NULL;
 
 	check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges));
-	check_symbol_range(name, addr, &percpu_range, 1);
 
 	/* include the type field in the symbol name, so that it gets
 	 * compressed together */
@@ -175,7 +168,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 	sym->len = len;
 	sym->sym[0] = type;
 	strcpy(sym_name(sym), name);
-	sym->percpu_absolute = false;
 
 	return sym;
 }
@@ -319,11 +311,6 @@ static int expand_symbol(const unsigned char *data, int len, char *result)
 	return total;
 }
 
-static bool symbol_absolute(const struct sym_entry *s)
-{
-	return s->percpu_absolute;
-}
-
 static int compare_names(const void *a, const void *b)
 {
 	int ret;
@@ -455,22 +442,11 @@ static void write_src(void)
 		 */
 
 		long long offset;
-		bool overflow;
-
-		if (!absolute_percpu) {
-			offset = table[i]->addr - relative_base;
-			overflow = offset < 0 || offset > UINT_MAX;
-		} else if (symbol_absolute(table[i])) {
-			offset = table[i]->addr;
-			overflow = offset < 0 || offset > INT_MAX;
-		} else {
-			offset = relative_base - table[i]->addr - 1;
-			overflow = offset < INT_MIN || offset >= 0;
-		}
-		if (overflow) {
+
+		offset = table[i]->addr - relative_base;
+		if (offset < 0 || offset > UINT_MAX) {
 			fprintf(stderr, "kallsyms failure: "
-				"%s symbol value %#llx out of range in relative mode\n",
-				symbol_absolute(table[i]) ? "absolute" : "relative",
+				"relative symbol value %#llx out of range\n",
 				table[i]->addr);
 			exit(EXIT_FAILURE);
 		}
@@ -725,36 +701,15 @@ static void sort_symbols(void)
 	qsort(table, table_cnt, sizeof(table[0]), compare_symbols);
 }
 
-static void make_percpus_absolute(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (symbol_in_range(table[i], &percpu_range, 1)) {
-			/*
-			 * Keep the 'A' override for percpu symbols to
-			 * ensure consistent behavior compared to older
-			 * versions of this tool.
-			 */
-			table[i]->sym[0] = 'A';
-			table[i]->percpu_absolute = true;
-		}
-}
-
 /* find the minimum non-absolute symbol address */
 static void record_relative_base(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (!symbol_absolute(table[i])) {
-			/*
-			 * The table is sorted by address.
-			 * Take the first non-absolute symbol value.
-			 */
-			relative_base = table[i]->addr;
-			return;
-		}
+	/*
+	 * The table is sorted by address.
+	 * Take the first symbol value.
+	 */
+	if (table_cnt)
+		relative_base = table[0]->addr;
 }
 
 int main(int argc, char **argv)
@@ -762,7 +717,6 @@ int main(int argc, char **argv)
 	while (1) {
 		static const struct option long_options[] = {
 			{"all-symbols",     no_argument, &all_symbols,     1},
-			{"absolute-percpu", no_argument, &absolute_percpu, 1},
 			{},
 		};
 
@@ -779,8 +733,6 @@ int main(int argc, char **argv)
 
 	read_map(argv[optind]);
 	shrink_table();
-	if (absolute_percpu)
-		make_percpus_absolute();
 	sort_symbols();
 	record_relative_base();
 	optimize_token_table();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 56a077d204cf..67e66333bd2a 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -144,10 +144,6 @@ kallsyms()
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
-	if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
-		kallsymopt="${kallsymopt} --absolute-percpu"
-	fi
-
 	info KSYMS "${2}.S"
 	scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
 
-- 
2.51.0