linux/arch/riscv/include/asm/checksum.h

93 lines
2.5 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Checksum routines
*
* Copyright (C) 2023 Rivos Inc.
*/
#ifndef __ASM_RISCV_CHECKSUM_H
#define __ASM_RISCV_CHECKSUM_H
#include <linux/in6.h>
#include <linux/uaccess.h>
#define ip_fast_csum ip_fast_csum
extern unsigned int do_csum(const unsigned char *buff, int len);
#define do_csum do_csum
/* Default version is sufficient for 32 bit */
#ifndef CONFIG_32BIT
#define _HAVE_ARCH_IPV6_CSUM
__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u32 len, __u8 proto, __wsum sum);
#endif
/* Define riscv versions of functions before importing asm-generic/checksum.h */
#include <asm-generic/checksum.h>
/**
* Quickly compute an IP checksum with the assumption that IPv4 headers will
* always be in multiples of 32-bits, and have an ihl of at least 5.
*
* @ihl: the number of 32 bit segments and must be greater than or equal to 5.
* @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
* riscv, defining IP headers to be aligned.
*/
static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
unsigned long csum = 0;
int pos = 0;
do {
csum += ((const unsigned int *)iph)[pos];
if (IS_ENABLED(CONFIG_32BIT))
csum += csum < ((const unsigned int *)iph)[pos];
} while (++pos < ihl);
/*
* ZBB only saves three instructions on 32-bit and five on 64-bit so not
* worth checking if supported without Alternatives.
*/
if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
unsigned long fold_temp;
work around gcc bugs with 'asm goto' with outputs We've had issues with gcc and 'asm goto' before, and we created a 'asm_volatile_goto()' macro for that in the past: see commits 3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation bug") and a9f180345f53 ("compiler/gcc4: Make quirk for asm_volatile_goto() unconditional"). Then, much later, we ended up removing the workaround in commit 43c249ea0b1e ("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'. but 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>
2024-02-09 12:39:31 -08:00
asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
:
: no_zbb);
if (IS_ENABLED(CONFIG_32BIT)) {
asm(".option push \n\
.option arch,+zbb \n\
not %[fold_temp], %[csum] \n\
rori %[csum], %[csum], 16 \n\
sub %[csum], %[fold_temp], %[csum] \n\
.option pop"
: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
} else {
asm(".option push \n\
.option arch,+zbb \n\
rori %[fold_temp], %[csum], 32 \n\
add %[csum], %[fold_temp], %[csum] \n\
srli %[csum], %[csum], 32 \n\
not %[fold_temp], %[csum] \n\
roriw %[csum], %[csum], 16 \n\
subw %[csum], %[fold_temp], %[csum] \n\
.option pop"
: [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
}
return (__force __sum16)(csum >> 16);
}
no_zbb:
#ifndef CONFIG_32BIT
csum += ror64(csum, 32);
csum >>= 32;
#endif
return csum_fold((__force __wsum)csum);
}
#endif /* __ASM_RISCV_CHECKSUM_H */