f70efe54b9
commit 68fb3ca0e408e00db1c3f8fccdfa19e274c033be upstream. We've had issues with gcc and 'asm goto' before, and we created a 'asm_volatile_goto()' macro for that in the past: see commits3f0116c323("compiler/gcc4: Add quirk for 'asm goto' miscompilation bug") anda9f180345f("compiler/gcc4: Make quirk for asm_volatile_goto() unconditional"). Then, much later, we ended up removing the workaround in commit43c249ea0b("compiler-gcc.h: remove ancient workaround for gcc PR 58670") because we no longer supported building the kernel with the affected gcc versions, but we left the macro uses around. Now, Sean Christopherson reports a new version of a very similar problem, which is fixed by re-applying that ancient workaround. But the problem in question is limited to only the 'asm goto with outputs' cases, so instead of re-introducing the old workaround as-is, let's rename and limit the workaround to just that much less common case. It looks like there are at least two separate issues that all hit in this area: (a) some versions of gcc don't mark the asm goto as 'volatile' when it has outputs: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 which is easy to work around by just adding the 'volatile' by hand. (b) Internal compiler errors: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 which are worked around by adding the extra empty 'asm' as a barrier, as in the original workaround. but the problem Sean sees may be a third thing since it involves bad code generation (not an ICE) even with the manually added 'volatile'. The same old workaround works for this case, even if this feels a bit like voodoo programming and may only be hiding the issue. Reported-and-tested-by: Sean Christopherson <seanjc@google.com> Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Uros Bizjak <ubizjak@gmail.com> Cc: Jakub Jelinek <jakub@redhat.com> Cc: Andrew Pinski <quic_apinski@quicinc.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
73 lines
1.9 KiB
C
73 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_ARC_JUMP_LABEL_H
|
|
#define _ASM_ARC_JUMP_LABEL_H
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/stringify.h>
|
|
#include <linux/types.h>
|
|
|
|
#define JUMP_LABEL_NOP_SIZE 4
|
|
|
|
/*
|
|
* NOTE about '.balign 4':
|
|
*
|
|
* To make atomic update of patched instruction available we need to guarantee
|
|
* that this instruction doesn't cross L1 cache line boundary.
|
|
*
|
|
* As of today we simply align instruction which can be patched by 4 byte using
|
|
* ".balign 4" directive. In that case patched instruction is aligned with one
|
|
* 16-bit NOP_S if this is required.
|
|
* However 'align by 4' directive is much stricter than it actually required.
|
|
* It's enough that our 32-bit instruction don't cross L1 cache line boundary /
|
|
* L1 I$ fetch block boundary which can be achieved by using
|
|
* ".bundle_align_mode" assembler directive. That will save us from adding
|
|
* useless NOP_S padding in most of the cases.
|
|
*
|
|
* TODO: switch to ".bundle_align_mode" directive using whin it will be
|
|
* supported by ARC toolchain.
|
|
*/
|
|
|
|
static __always_inline bool arch_static_branch(struct static_key *key,
|
|
bool branch)
|
|
{
|
|
asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
|
|
"1: \n"
|
|
"nop \n"
|
|
".pushsection __jump_table, \"aw\" \n"
|
|
".word 1b, %l[l_yes], %c0 \n"
|
|
".popsection \n"
|
|
: : "i" (&((char *)key)[branch]) : : l_yes);
|
|
|
|
return false;
|
|
l_yes:
|
|
return true;
|
|
}
|
|
|
|
static __always_inline bool arch_static_branch_jump(struct static_key *key,
|
|
bool branch)
|
|
{
|
|
asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
|
|
"1: \n"
|
|
"b %l[l_yes] \n"
|
|
".pushsection __jump_table, \"aw\" \n"
|
|
".word 1b, %l[l_yes], %c0 \n"
|
|
".popsection \n"
|
|
: : "i" (&((char *)key)[branch]) : : l_yes);
|
|
|
|
return false;
|
|
l_yes:
|
|
return true;
|
|
}
|
|
|
|
typedef u32 jump_label_t;
|
|
|
|
struct jump_entry {
|
|
jump_label_t code;
|
|
jump_label_t target;
|
|
jump_label_t key;
|
|
};
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
#endif
|