From: Andrew Murray <andrew.murray@arm.com> To: Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will.deacon@arm.com>, Peter Zijlstra <peterz@infradead.org>, Ard.Biesheuvel@arm.com Cc: Boqun Feng <boqun.feng@gmail.com>, linux-arm-kernel@lists.infradead.org Subject: [PATCH v1 2/5] arm64: Use correct ll/sc atomic constraints Date: Thu, 16 May 2019 16:53:41 +0100 Message-ID: <20190516155344.24060-3-andrew.murray@arm.com> (raw) In-Reply-To: <20190516155344.24060-1-andrew.murray@arm.com> For many of the ll/sc atomic operations we use the 'I' machine constraint regardless to the instruction used - this may not be optimal. Let's add an additional parameter to the ATOMIC_xx macros that allows the caller to specify an appropriate machine constraint. Let's also improve __CMPXCHG_CASE by replacing the 'K' constraint with a caller provided constraint. Please note that whilst we would like to use the 'K' constraint on 32 bit operations, we choose not to provide any constraint to avoid a GCC bug which results in a build error. Earlier versions of GCC (no later than 8.1.0) appear to incorrectly handle the 'K' constraint for the value 4294967295. Signed-off-by: Andrew Murray <andrew.murray@arm.com> --- arch/arm64/include/asm/atomic_ll_sc.h | 89 ++++++++++++++------------- 1 file changed, 47 insertions(+), 42 deletions(-) diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index e321293e0c89..c2ce0c75fc0b 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -37,7 +37,7 @@ * (the optimize attribute silently ignores these options). */ -#define ATOMIC_OP(op, asm_op) \ +#define ATOMIC_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v)) \ { \ @@ -51,11 +51,11 @@ __LL_SC_PREFIX(arch_atomic_##op(int i, atomic_t *v)) \ " stxr %w1, %w0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(arch_atomic_##op); -#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE int \ __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v)) \ { \ @@ -70,14 +70,14 @@ __LL_SC_PREFIX(arch_atomic_##op##_return##name(int i, atomic_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(arch_atomic_##op##_return##name); -#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ __LL_SC_INLINE int \ __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v)) \ { \ @@ -92,7 +92,7 @@ __LL_SC_PREFIX(arch_atomic_fetch_##op##name(int i, atomic_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -110,8 +110,8 @@ __LL_SC_EXPORT(arch_atomic_fetch_##op##name); ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, sub) +ATOMIC_OPS(add, add, I) +ATOMIC_OPS(sub, sub, J) #undef ATOMIC_OPS #define ATOMIC_OPS(...) \ @@ -121,17 +121,17 @@ ATOMIC_OPS(sub, sub) ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(and, and) -ATOMIC_OPS(andnot, bic) -ATOMIC_OPS(or, orr) -ATOMIC_OPS(xor, eor) +ATOMIC_OPS(and, and, K) +ATOMIC_OPS(andnot, bic, ) +ATOMIC_OPS(or, orr, K) +ATOMIC_OPS(xor, eor, K) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define ATOMIC64_OP(op, asm_op) \ +#define ATOMIC64_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v)) \ { \ @@ -145,11 +145,11 @@ __LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v)) \ " stxr %w1, %0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(arch_atomic64_##op); -#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\ { \ @@ -164,14 +164,14 @@ __LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(arch_atomic64_##op##_return##name); -#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v)) \ { \ @@ -186,7 +186,7 @@ __LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -204,8 +204,8 @@ __LL_SC_EXPORT(arch_atomic64_fetch_##op##name); ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(add, add) -ATOMIC64_OPS(sub, sub) +ATOMIC64_OPS(add, add, I) +ATOMIC64_OPS(sub, sub, J) #undef ATOMIC64_OPS #define ATOMIC64_OPS(...) \ @@ -215,10 +215,10 @@ ATOMIC64_OPS(sub, sub) ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(and, and) -ATOMIC64_OPS(andnot, bic) -ATOMIC64_OPS(or, orr) -ATOMIC64_OPS(xor, eor) +ATOMIC64_OPS(and, and, K) +ATOMIC64_OPS(andnot, bic, ) +ATOMIC64_OPS(or, orr, K) +ATOMIC64_OPS(xor, eor, K) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP @@ -248,7 +248,7 @@ __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v)) } __LL_SC_EXPORT(arch_atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ __LL_SC_INLINE u##sz \ __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ unsigned long old, \ @@ -276,29 +276,34 @@ __LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ [v] "+Q" (*(u##sz *)ptr) \ - : [old] "Kr" (old), [new] "r" (new) \ + : [old] #constraint "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } \ __LL_SC_EXPORT(__cmpxchg_case_##name##sz); -__CMPXCHG_CASE(w, b, , 8, , , , ) -__CMPXCHG_CASE(w, h, , 16, , , , ) -__CMPXCHG_CASE(w, , , 32, , , , ) -__CMPXCHG_CASE( , , , 64, , , , ) -__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory") -__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory") -__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory") -__CMPXCHG_CASE( , , acq_, 64, , a, , "memory") -__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory") -__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory") -__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory") -__CMPXCHG_CASE( , , rel_, 64, , , l, "memory") -__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory") -__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory") +/* + * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly + * handle the 'K' constraint for the value 4294967295 - thus we use no + * constraint for 32 bit operations. + */ +__CMPXCHG_CASE(w, b, , 8, , , , , ) +__CMPXCHG_CASE(w, h, , 16, , , , , ) +__CMPXCHG_CASE(w, , , 32, , , , , ) +__CMPXCHG_CASE( , , , 64, , , , , L) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", ) +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", ) +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", ) +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", ) +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", ) +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", ) +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", ) +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE -- 2.21.0 _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply index Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-05-16 15:53 [PATCH v1 0/5] arm64: avoid out-of-line ll/sc atomics Andrew Murray 2019-05-16 15:53 ` [PATCH v1 1/5] jump_label: Don't warn on __exit jump entries Andrew Murray 2019-05-16 15:53 ` Andrew Murray [this message] 2019-05-16 15:53 ` [PATCH v1 3/5] arm64: atomics: avoid out-of-line ll/sc atomics Andrew Murray 2019-05-16 15:53 ` [PATCH v1 4/5] arm64: avoid using hard-coded registers for LSE atomics Andrew Murray 2019-05-16 15:53 ` [PATCH v1 5/5] arm64: atomics: remove atomic_ll_sc compilation unit Andrew Murray 2019-05-17 7:24 ` [PATCH v1 0/5] arm64: avoid out-of-line ll/sc atomics Peter Zijlstra 2019-05-17 10:08 ` Andrew Murray 2019-05-17 10:29 ` Ard Biesheuvel 2019-05-22 10:45 ` Andrew Murray 2019-05-22 11:44 ` Ard Biesheuvel 2019-05-22 15:36 ` Andrew Murray 2019-05-17 12:05 ` Peter Zijlstra 2019-05-17 12:19 ` Ard Biesheuvel
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=20190516155344.24060-3-andrew.murray@arm.com \ --to=andrew.murray@arm.com \ --cc=Ard.Biesheuvel@arm.com \ --cc=boqun.feng@gmail.com \ --cc=catalin.marinas@arm.com \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=peterz@infradead.org \ --cc=will.deacon@arm.com \ /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
Linux-ARM-Kernel Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/linux-arm-kernel/0 linux-arm-kernel/git/0.git git clone --mirror https://lore.kernel.org/linux-arm-kernel/1 linux-arm-kernel/git/1.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 linux-arm-kernel linux-arm-kernel/ https://lore.kernel.org/linux-arm-kernel \ linux-arm-kernel@lists.infradead.org public-inbox-index linux-arm-kernel Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.infradead.lists.linux-arm-kernel AGPL code for this site: git clone https://public-inbox.org/public-inbox.git