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

@@ -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);

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
+	xorl	%eax, %eax
-	movl	%edx, %eax
+	xorl	%edx, %edx
-	shrq	$32,  %rdx
 	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.
+	/*
-	 *
+	 * Set up GSBASE.
-	 * 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.
 	 */
 	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

arch/x86/kernel/setup_percpu.c

@@ -23,18 +23,10 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-#ifdef CONFIG_X86_64
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
-#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;
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
-	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
 EXPORT_SYMBOL(__per_cpu_offset);
 
 /*

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

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
+	xorl %eax, %eax
-	movq %edx, %eax
+	xorl %edx, %edx
-	shrq $32, %rdx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */

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 0;
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
 }
 
 
@@ -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)

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.
+	/*
-	 *
+	 * Set up GSBASE.
-	 * 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.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
+	xorl	%eax, %eax
-	cdq
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi

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