Files
linux/arch/x86/include/asm/page_64.h
Nathan Chancellor 9b041a4b66 x86/mm: Ensure clear_page() variants always have __kcfi_typeid_ symbols
When building with CONFIG_CFI=y and CONFIG_LTO_CLANG_FULL=y, there is a series
of errors from the various versions of clear_page() not having __kcfi_typeid_
symbols.

  $ cat kernel/configs/repro.config
  CONFIG_CFI=y
  # CONFIG_LTO_NONE is not set
  CONFIG_LTO_CLANG_FULL=y

  $ make -skj"$(nproc)" ARCH=x86_64 LLVM=1 clean defconfig repro.config bzImage
  ld.lld: error: undefined symbol: __kcfi_typeid_clear_page_rep
  >>> referenced by ld-temp.o
  >>>               vmlinux.o:(__cfi_clear_page_rep)

  ld.lld: error: undefined symbol: __kcfi_typeid_clear_page_orig
  >>> referenced by ld-temp.o
  >>>               vmlinux.o:(__cfi_clear_page_orig)

  ld.lld: error: undefined symbol: __kcfi_typeid_clear_page_erms
  >>> referenced by ld-temp.o
  >>>               vmlinux.o:(__cfi_clear_page_erms)

With full LTO, it is possible for LLVM to realize that these functions never
have their address taken (as they are only used within an alternative, which
will make them a direct call) across the whole kernel and either drop or skip
generating their kCFI type identification symbols.

clear_page_{rep,orig,erms}() are defined in clear_page_64.S with
SYM_TYPED_FUNC_START as a result of

  2981557cb0 ("x86,kcfi: Fix EXPORT_SYMBOL vs kCFI"),

as exported functions are free to be called indirectly thus need kCFI type
identifiers.

Use KCFI_REFERENCE with these clear_page() functions to force LLVM to see
these functions as address-taken and generate then keep the kCFI type
identifiers.

Fixes: 2981557cb0 ("x86,kcfi: Fix EXPORT_SYMBOL vs kCFI")
Closes: https://github.com/ClangBuiltLinux/linux/issues/2128
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://patch.msgid.link/20251013-x86-fix-clear_page-cfi-full-lto-errors-v1-1-d69534c0be61@kernel.org
2025-10-31 22:47:24 +01:00

106 lines
3.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PAGE_64_H
#define _ASM_X86_PAGE_64_H
#include <asm/page_64_types.h>
#ifndef __ASSEMBLER__
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <linux/kmsan-checks.h>
/* duplicated to the one in bootmem.h */
extern unsigned long max_pfn;
extern unsigned long phys_base;
extern unsigned long page_offset_base;
extern unsigned long vmalloc_base;
extern unsigned long vmemmap_base;
extern unsigned long direct_map_physmem_end;
static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
{
unsigned long y = x - __START_KERNEL_map;
/* use the carry flag to determine if x was < __START_KERNEL_map */
x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET));
return x;
}
#ifdef CONFIG_DEBUG_VIRTUAL
extern unsigned long __phys_addr(unsigned long);
extern unsigned long __phys_addr_symbol(unsigned long);
#else
#define __phys_addr(x) __phys_addr_nodebug(x)
#define __phys_addr_symbol(x) \
((unsigned long)(x) - __START_KERNEL_map + phys_base)
#endif
#define __phys_reloc_hide(x) (x)
void clear_page_orig(void *page);
void clear_page_rep(void *page);
void clear_page_erms(void *page);
KCFI_REFERENCE(clear_page_orig);
KCFI_REFERENCE(clear_page_rep);
KCFI_REFERENCE(clear_page_erms);
static inline void clear_page(void *page)
{
/*
* Clean up KMSAN metadata for the page being cleared. The assembly call
* below clobbers @page, so we perform unpoisoning before it.
*/
kmsan_unpoison_memory(page, PAGE_SIZE);
alternative_call_2(clear_page_orig,
clear_page_rep, X86_FEATURE_REP_GOOD,
clear_page_erms, X86_FEATURE_ERMS,
"=D" (page),
"D" (page),
"cc", "memory", "rax", "rcx");
}
void copy_page(void *to, void *from);
KCFI_REFERENCE(copy_page);
/*
* User space process size. This is the first address outside the user range.
* There are a few constraints that determine this:
*
* On Intel CPUs, if a SYSCALL instruction is at the highest canonical
* address, then that syscall will enter the kernel with a
* non-canonical return address, and SYSRET will explode dangerously.
* We avoid this particular problem by preventing anything
* from being mapped at the maximum canonical address.
*
* On AMD CPUs in the Ryzen family, there's a nasty bug in which the
* CPUs malfunction if they execute code from the highest canonical page.
* They'll speculate right off the end of the canonical space, and
* bad things happen. This is worked around in the same way as the
* Intel problem.
*
* With page table isolation enabled, we map the LDT in ... [stay tuned]
*/
static __always_inline unsigned long task_size_max(void)
{
unsigned long ret;
alternative_io("movq %[small],%0","movq %[large],%0",
X86_FEATURE_LA57,
"=r" (ret),
[small] "i" ((1ul << 47)-PAGE_SIZE),
[large] "i" ((1ul << 56)-PAGE_SIZE));
return ret;
}
#endif /* !__ASSEMBLER__ */
#ifdef CONFIG_X86_VSYSCALL_EMULATION
# define __HAVE_ARCH_GATE_AREA 1
#endif
#endif /* _ASM_X86_PAGE_64_H */