From: Peter Zijlstra <peterz@infradead.org>
To: torvalds@linux-foundation.org
Cc: corbet@lwn.net, will@kernel.org, peterz@infradead.org,
boqun.feng@gmail.com, mark.rutland@arm.com,
catalin.marinas@arm.com, dennis@kernel.org, tj@kernel.org,
cl@linux.com, hca@linux.ibm.com, gor@linux.ibm.com,
agordeev@linux.ibm.com, borntraeger@linux.ibm.com,
svens@linux.ibm.com, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
hpa@zytor.com, joro@8bytes.org, suravee.suthikulpanit@amd.com,
robin.murphy@arm.com, dwmw2@infradead.org,
baolu.lu@linux.intel.com, Arnd Bergmann <arnd@arndb.de>,
Herbert Xu <herbert@gondor.apana.org.au>,
davem@davemloft.net, penberg@kernel.org, rientjes@google.com,
iamjoonsoo.kim@lge.com, Andrew Morton <akpm@linux-foundation.org>,
vbabka@suse.cz, roman.gushchin@linux.dev, 42.hyeyoo@gmail.com,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-s390@vger.kernel.org,
iommu@lists.linux.dev, linux-arch@vger.kernel.org,
linux-crypto@vger.kernel.org, sfr@canb.auug.org.au,
mpe@ellerman.id.au, James.Bottomley@hansenpartnership.com,
deller@gmx.de, linux-parisc@vger.kernel.org
Subject: [PATCH 03/12] arch: Introduce arch_{,try_}_cmpxchg128{,_local}()
Date: Wed, 31 May 2023 15:08:36 +0200 [thread overview]
Message-ID: <20230531132323.452120708@infradead.org> (raw)
In-Reply-To: 20230531130833.635651916@infradead.org
For all architectures that currently support cmpxchg_double()
implement the cmpxchg128() family of functions that is basically the
same but with a saner interface.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
---
arch/arm64/include/asm/atomic_ll_sc.h | 41 +++++++++++++++++++++
arch/arm64/include/asm/atomic_lse.h | 31 ++++++++++++++++
arch/arm64/include/asm/cmpxchg.h | 26 +++++++++++++
arch/s390/include/asm/cmpxchg.h | 14 +++++++
arch/x86/include/asm/cmpxchg_32.h | 3 +
arch/x86/include/asm/cmpxchg_64.h | 64 +++++++++++++++++++++++++++++++++-
6 files changed, 177 insertions(+), 2 deletions(-)
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -326,6 +326,47 @@ __CMPXCHG_DBL( , , , )
__CMPXCHG_DBL(_mb, dmb ish, l, "memory")
#undef __CMPXCHG_DBL
+
+union __u128_halves {
+ u128 full;
+ struct {
+ u64 low, high;
+ };
+};
+
+#define __CMPXCHG128(name, mb, rel, cl...) \
+static __always_inline u128 \
+__ll_sc__cmpxchg128##name(volatile u128 *ptr, u128 old, u128 new) \
+{ \
+ union __u128_halves r, o = { .full = (old) }, \
+ n = { .full = (new) }; \
+ unsigned int tmp; \
+ \
+ asm volatile("// __cmpxchg128" #name "\n" \
+ " prfm pstl1strm, %[v]\n" \
+ "1: ldxp %[rl], %[rh], %[v]\n" \
+ " cmp %[rl], %[ol]\n" \
+ " ccmp %[rh], %[oh], 0, eq\n" \
+ " b.ne 2f\n" \
+ " st" #rel "xp %w[tmp], %[nl], %[nh], %[v]\n" \
+ " cbnz %w[tmp], 1b\n" \
+ " " #mb "\n" \
+ "2:" \
+ : [v] "+Q" (*(u128 *)ptr), \
+ [rl] "=&r" (r.low), [rh] "=&r" (r.high), \
+ [tmp] "=&r" (tmp) \
+ : [ol] "r" (o.low), [oh] "r" (o.high), \
+ [nl] "r" (n.low), [nh] "r" (n.high) \
+ : "cc", ##cl); \
+ \
+ return r.full; \
+}
+
+__CMPXCHG128( , , )
+__CMPXCHG128(_mb, dmb ish, l, "memory")
+
+#undef __CMPXCHG128
+
#undef K
#endif /* __ASM_ATOMIC_LL_SC_H */
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -317,4 +317,35 @@ __CMPXCHG_DBL(_mb, al, "memory")
#undef __CMPXCHG_DBL
+#define __CMPXCHG128(name, mb, cl...) \
+static __always_inline u128 \
+__lse__cmpxchg128##name(volatile u128 *ptr, u128 old, u128 new) \
+{ \
+ union __u128_halves r, o = { .full = (old) }, \
+ n = { .full = (new) }; \
+ register unsigned long x0 asm ("x0") = o.low; \
+ register unsigned long x1 asm ("x1") = o.high; \
+ register unsigned long x2 asm ("x2") = n.low; \
+ register unsigned long x3 asm ("x3") = n.high; \
+ register unsigned long x4 asm ("x4") = (unsigned long)ptr; \
+ \
+ asm volatile( \
+ __LSE_PREAMBLE \
+ " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
+ : [old1] "+&r" (x0), [old2] "+&r" (x1), \
+ [v] "+Q" (*(u128 *)ptr) \
+ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
+ [oldval1] "r" (o.low), [oldval2] "r" (o.high) \
+ : cl); \
+ \
+ r.low = x0; r.high = x1; \
+ \
+ return r.full; \
+}
+
+__CMPXCHG128( , )
+__CMPXCHG128(_mb, al, "memory")
+
+#undef __CMPXCHG128
+
#endif /* __ASM_ATOMIC_LSE_H */
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -146,6 +146,19 @@ __CMPXCHG_DBL(_mb)
#undef __CMPXCHG_DBL
+#define __CMPXCHG128(name) \
+static inline u128 __cmpxchg128##name(volatile u128 *ptr, \
+ u128 old, u128 new) \
+{ \
+ return __lse_ll_sc_body(_cmpxchg128##name, \
+ ptr, old, new); \
+}
+
+__CMPXCHG128( )
+__CMPXCHG128(_mb)
+
+#undef __CMPXCHG128
+
#define __CMPXCHG_GEN(sfx) \
static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \
unsigned long old, \
@@ -228,6 +241,19 @@ __CMPXCHG_GEN(_mb)
__ret; \
})
+/* cmpxchg128 */
+#define system_has_cmpxchg128() 1
+
+#define arch_cmpxchg128(ptr, o, n) \
+({ \
+ __cmpxchg128_mb((ptr), (o), (n)); \
+})
+
+#define arch_cmpxchg128_local(ptr, o, n) \
+({ \
+ __cmpxchg128((ptr), (o), (n)); \
+})
+
#define __CMPWAIT_CASE(w, sfx, sz) \
static inline void __cmpwait_case_##sz(volatile void *ptr, \
unsigned long val) \
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -224,4 +224,18 @@ static __always_inline int __cmpxchg_dou
(unsigned long)(n1), (unsigned long)(n2)); \
})
+#define system_has_cmpxchg128() 1
+
+static __always_inline u128 arch_cmpxchg128(volatile u128 *ptr, u128 old, u128 new)
+{
+ asm volatile(
+ " cdsg %[old],%[new],%[ptr]\n"
+ : [old] "+d" (old), [ptr] "+QS" (*ptr)
+ : [new] "d" (new)
+ : "memory", "cc");
+ return old;
+}
+
+#define arch_cmpxchg128 arch_cmpxchg128
+
#endif /* __ASM_CMPXCHG_H */
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -103,6 +103,7 @@ static inline bool __try_cmpxchg64(volat
#endif
-#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8)
+#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8)
+#define system_has_cmpxchg64() boot_cpu_has(X86_FEATURE_CX8)
#endif /* _ASM_X86_CMPXCHG_32_H */
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -20,6 +20,68 @@
arch_try_cmpxchg((ptr), (po), (n)); \
})
-#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
+union __u128_halves {
+ u128 full;
+ struct {
+ u64 low, high;
+ };
+};
+
+#define __arch_cmpxchg128(_ptr, _old, _new, _lock) \
+({ \
+ union __u128_halves o = { .full = (_old), }, \
+ n = { .full = (_new), }; \
+ \
+ asm volatile(_lock "cmpxchg16b %[ptr]" \
+ : [ptr] "+m" (*(_ptr)), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ o.full; \
+})
+
+static __always_inline u128 arch_cmpxchg128(volatile u128 *ptr, u128 old, u128 new)
+{
+ return __arch_cmpxchg128(ptr, old, new, LOCK_PREFIX);
+}
+
+static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, u128 new)
+{
+ return __arch_cmpxchg128(ptr, old, new,);
+}
+
+#define __arch_try_cmpxchg128(_ptr, _oldp, _new, _lock) \
+({ \
+ union __u128_halves o = { .full = *(_oldp), }, \
+ n = { .full = (_new), }; \
+ bool ret; \
+ \
+ asm volatile(_lock "cmpxchg16b %[ptr]" \
+ CC_SET(e) \
+ : CC_OUT(e) (ret), \
+ [ptr] "+m" (*ptr), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ if (unlikely(!ret)) \
+ *(_oldp) = o.full; \
+ \
+ likely(ret); \
+})
+
+static __always_inline bool arch_try_cmpxchg128(volatile u128 *ptr, u128 *oldp, u128 new)
+{
+ return __arch_try_cmpxchg128(ptr, oldp, new, LOCK_PREFIX);
+}
+
+static __always_inline bool arch_try_cmpxchg128_local(volatile u128 *ptr, u128 *oldp, u128 new)
+{
+ return __arch_try_cmpxchg128(ptr, oldp, new,);
+}
+
+#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
+#define system_has_cmpxchg128() boot_cpu_has(X86_FEATURE_CX16)
#endif /* _ASM_X86_CMPXCHG_64_H */
next prev parent reply other threads:[~2023-05-31 13:28 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-31 13:08 [PATCH 00/12] Introduce cmpxchg128() -- aka. the demise of cmpxchg_double() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 01/12] cyrpto/b128ops: Remove struct u128 Peter Zijlstra
2023-05-31 13:08 ` [PATCH 02/12] types: Introduce [us]128 Peter Zijlstra
2023-05-31 13:08 ` Peter Zijlstra [this message]
2023-05-31 13:08 ` [PATCH 04/12] instrumentation: Wire up cmpxchg128() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 05/12] percpu: Add {raw,this}_cpu_try_cmpxchg() Peter Zijlstra
2023-06-09 16:10 ` [PATCH v2 5/12] " Konrad Dybcio
2023-06-09 16:13 ` Nathan Chancellor
2023-06-09 16:20 ` Konrad Dybcio
2023-05-31 13:08 ` [PATCH 06/12] percpu: Wire up cmpxchg128 Peter Zijlstra
2023-05-31 13:08 ` [PATCH 07/12] percpu: #ifndef __SIZEOF_INT128__ Peter Zijlstra
2023-05-31 14:21 ` Arnd Bergmann
2023-05-31 15:50 ` Peter Zijlstra
2023-06-01 10:14 ` [PATCH v2 07/12] parisc/percpu: Work around the lack of __SIZEOF_INT128__ Peter Zijlstra
2023-06-01 10:32 ` Helge Deller
2023-06-01 10:50 ` Peter Zijlstra
2023-06-01 21:08 ` Sam James
2023-06-01 13:29 ` Linus Torvalds
2023-06-01 17:38 ` Masahiro Yamada
2023-06-02 14:39 ` Peter Zijlstra
2023-06-02 14:50 ` Mark Rutland
2023-06-02 16:09 ` Linus Torvalds
2023-06-02 17:00 ` H. Peter Anvin
2023-06-02 19:10 ` Peter Zijlstra
2023-06-02 19:20 ` H. Peter Anvin
2023-06-02 19:40 ` Peter Zijlstra
2023-06-02 19:57 ` Linus Torvalds
2023-06-02 20:42 ` Helge Deller
2023-05-31 13:08 ` [PATCH 08/12] x86,amd_iommu: Replace cmpxchg_double() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 09/12] x86,intel_iommu: " Peter Zijlstra
2023-05-31 13:08 ` [PATCH 10/12] slub: " Peter Zijlstra
2023-05-31 13:08 ` [PATCH 11/12] arch: Remove cmpxchg_double Peter Zijlstra
2023-05-31 13:08 ` [PATCH 12/12] s390/cpum_sf: Convert to cmpxchg128() Peter Zijlstra
2023-05-31 14:47 ` [PATCH 00/12] Introduce cmpxchg128() -- aka. the demise of cmpxchg_double() Mark Rutland
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230531132323.452120708@infradead.org \
--to=peterz@infradead.org \
--cc=42.hyeyoo@gmail.com \
--cc=James.Bottomley@hansenpartnership.com \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=baolu.lu@linux.intel.com \
--cc=boqun.feng@gmail.com \
--cc=borntraeger@linux.ibm.com \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=cl@linux.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=davem@davemloft.net \
--cc=deller@gmx.de \
--cc=dennis@kernel.org \
--cc=dwmw2@infradead.org \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=hpa@zytor.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-parisc@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=penberg@kernel.org \
--cc=rientjes@google.com \
--cc=robin.murphy@arm.com \
--cc=roman.gushchin@linux.dev \
--cc=sfr@canb.auug.org.au \
--cc=suravee.suthikulpanit@amd.com \
--cc=svens@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).