From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: locking/spinlock, arch: Update and fix spin_unlock_wait() implementations This patch updates/fixes all spin_unlock_wait() implementations. The update is in semantics; where it previously was only a control dependency, we now upgrade to a full load-acquire to match the store-release from the spin_unlock() we waited on. This ensures that when spin_unlock_wait() returns, we're guaranteed to observe the full critical section we waited on. This fixes a number of spin_unlock_wait() users that (not unreasonably) rely on this. I also fixed a number of ticket lock versions to only wait on the current lock holder, instead of for a full unlock, as this is sufficient. Furthermore; again for ticket locks; I added an smp_rmb() in between the initial ticket load and the spin loop testing the current value because I could not convince myself the address dependency is sufficient, esp. if the loads are of different sizes. I'm more than happy to remove this smp_rmb() again if people are certain the address dependency does indeed work as expected. Note: PPC32 will be fixed independently Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: chris@zankel.net Cc: cmetcalf@mellanox.com Cc: davem@davemloft.net Cc: dhowells@redhat.com Cc: james.hogan@imgtec.com Cc: jejb@parisc-linux.org Cc: linux@armlinux.org.uk Cc: mpe@ellerman.id.au Cc: ralf@linux-mips.org Cc: realmz6@gmail.com Cc: rkuo@codeaurora.org Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: vgupta@synopsys.com Cc: ysato@users.sourceforge.jp Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/sparc/include/asm/spinlock_32.h | 7 +++++-- arch/sparc/include/asm/spinlock_64.h | 10 +++++++--- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/sparc') diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index bcc98fc35281..d9c5876c6121 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -9,12 +9,15 @@ #ifndef __ASSEMBLY__ #include +#include #include /* for cpu_relax */ #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 968917694978..87990b7c6b0d 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -8,6 +8,9 @@ #ifndef __ASSEMBLY__ +#include +#include + /* To get debugging spinlocks which detect and catch * deadlock situations, set CONFIG_DEBUG_SPINLOCK * and rebuild your kernel. @@ -23,9 +26,10 @@ #define arch_spin_is_locked(lp) ((lp)->lock != 0) -#define arch_spin_unlock_wait(lp) \ - do { rmb(); \ - } while((lp)->lock) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { -- cgit v1.2.3-70-g09d2 From 3a1adb23a52c920304239efff377d3bc967febc2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 01:16:04 +0200 Subject: locking/atomic, arch/sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Implement FETCH-OP atomic primitives, these are very similar to the existing OP-RETURN primitives we already have, except they return the value of the atomic variable _before_ modification. This is especially useful for irreversible operations -- such as bitops (because it becomes impossible to reconstruct the state prior to modification). Signed-off-by: Peter Zijlstra (Intel) Acked-by: David S. Miller Cc: Andrew Morton Cc: James Y Knight Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: sparclinux@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/sparc/include/asm/atomic.h | 1 + arch/sparc/include/asm/atomic_32.h | 15 ++++++++-- arch/sparc/include/asm/atomic_64.h | 16 +++++++--- arch/sparc/lib/atomic32.c | 29 ++++++++++-------- arch/sparc/lib/atomic_64.S | 61 +++++++++++++++++++++++++++++++------- arch/sparc/lib/ksyms.c | 17 ++++++++--- 6 files changed, 105 insertions(+), 34 deletions(-) (limited to 'arch/sparc') diff --git a/arch/sparc/include/asm/atomic.h b/arch/sparc/include/asm/atomic.h index 8ff83d8cc33f..1f741bcc73b7 100644 --- a/arch/sparc/include/asm/atomic.h +++ b/arch/sparc/include/asm/atomic.h @@ -5,4 +5,5 @@ #else #include #endif +#define atomic_fetch_or atomic_fetch_or #endif diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 7dcbebbcaec6..5cfb20a599d9 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -20,9 +20,10 @@ #define ATOMIC_INIT(i) { (i) } int atomic_add_return(int, atomic_t *); -void atomic_and(int, atomic_t *); -void atomic_or(int, atomic_t *); -void atomic_xor(int, atomic_t *); +int atomic_fetch_add(int, atomic_t *); +int atomic_fetch_and(int, atomic_t *); +int atomic_fetch_or(int, atomic_t *); +int atomic_fetch_xor(int, atomic_t *); int atomic_cmpxchg(atomic_t *, int, int); int atomic_xchg(atomic_t *, int); int __atomic_add_unless(atomic_t *, int, int); @@ -35,7 +36,15 @@ void atomic_set(atomic_t *, int); #define atomic_inc(v) ((void)atomic_add_return( 1, (v))) #define atomic_dec(v) ((void)atomic_add_return( -1, (v))) +#define atomic_fetch_or atomic_fetch_or + +#define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) +#define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) +#define atomic_xor(i, v) ((void)atomic_fetch_xor((i), (v))) + #define atomic_sub_return(i, v) (atomic_add_return(-(int)(i), (v))) +#define atomic_fetch_sub(i, v) (atomic_fetch_add (-(int)(i), (v))) + #define atomic_inc_return(v) (atomic_add_return( 1, (v))) #define atomic_dec_return(v) (atomic_add_return( -1, (v))) diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index f2fbf9e16faf..24827a3f733a 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -28,16 +28,24 @@ void atomic64_##op(long, atomic64_t *); int atomic_##op##_return(int, atomic_t *); \ long atomic64_##op##_return(long, atomic64_t *); -#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) +#define ATOMIC_FETCH_OP(op) \ +int atomic_fetch_##op(int, atomic_t *); \ +long atomic64_fetch_##op(long, atomic64_t *); + +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op) ATOMIC_OPS(add) ATOMIC_OPS(sub) -ATOMIC_OP(and) -ATOMIC_OP(or) -ATOMIC_OP(xor) +#undef ATOMIC_OPS +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) + +ATOMIC_OPS(and) +ATOMIC_OPS(or) +ATOMIC_OPS(xor) #undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index b9d63c0a7aab..2c373329d5cb 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -27,39 +27,44 @@ static DEFINE_SPINLOCK(dummy); #endif /* SMP */ -#define ATOMIC_OP_RETURN(op, c_op) \ -int atomic_##op##_return(int i, atomic_t *v) \ +#define ATOMIC_FETCH_OP(op, c_op) \ +int atomic_fetch_##op(int i, atomic_t *v) \ { \ int ret; \ unsigned long flags; \ spin_lock_irqsave(ATOMIC_HASH(v), flags); \ \ - ret = (v->counter c_op i); \ + ret = v->counter; \ + v->counter c_op i; \ \ spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \ return ret; \ } \ -EXPORT_SYMBOL(atomic_##op##_return); +EXPORT_SYMBOL(atomic_fetch_##op); -#define ATOMIC_OP(op, c_op) \ -void atomic_##op(int i, atomic_t *v) \ +#define ATOMIC_OP_RETURN(op, c_op) \ +int atomic_##op##_return(int i, atomic_t *v) \ { \ + int ret; \ unsigned long flags; \ spin_lock_irqsave(ATOMIC_HASH(v), flags); \ \ - v->counter c_op i; \ + ret = (v->counter c_op i); \ \ spin_unlock_irqrestore(ATOMIC_HASH(v), flags); \ + return ret; \ } \ -EXPORT_SYMBOL(atomic_##op); +EXPORT_SYMBOL(atomic_##op##_return); ATOMIC_OP_RETURN(add, +=) -ATOMIC_OP(and, &=) -ATOMIC_OP(or, |=) -ATOMIC_OP(xor, ^=) +ATOMIC_FETCH_OP(add, +=) +ATOMIC_FETCH_OP(and, &=) +ATOMIC_FETCH_OP(or, |=) +ATOMIC_FETCH_OP(xor, ^=) + +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN -#undef ATOMIC_OP int atomic_xchg(atomic_t *v, int new) { diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S index d6b0363f345b..a5c5a0279ccc 100644 --- a/arch/sparc/lib/atomic_64.S +++ b/arch/sparc/lib/atomic_64.S @@ -9,10 +9,11 @@ .text - /* Two versions of the atomic routines, one that + /* Three versions of the atomic routines, one that * does not return a value and does not perform - * memory barriers, and a second which returns - * a value and does the barriers. + * memory barriers, and a two which return + * a value, the new and old value resp. and does the + * barriers. */ #define ATOMIC_OP(op) \ @@ -43,15 +44,34 @@ ENTRY(atomic_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \ 2: BACKOFF_SPIN(%o2, %o3, 1b); \ ENDPROC(atomic_##op##_return); -#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) +#define ATOMIC_FETCH_OP(op) \ +ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \ + BACKOFF_SETUP(%o2); \ +1: lduw [%o1], %g1; \ + op %g1, %o0, %g7; \ + cas [%o1], %g1, %g7; \ + cmp %g1, %g7; \ + bne,pn %icc, BACKOFF_LABEL(2f, 1b); \ + nop; \ + retl; \ + sra %g1, 0, %o0; \ +2: BACKOFF_SPIN(%o2, %o3, 1b); \ +ENDPROC(atomic_fetch_##op); + +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op) ATOMIC_OPS(add) ATOMIC_OPS(sub) -ATOMIC_OP(and) -ATOMIC_OP(or) -ATOMIC_OP(xor) #undef ATOMIC_OPS +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) + +ATOMIC_OPS(and) +ATOMIC_OPS(or) +ATOMIC_OPS(xor) + +#undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP @@ -83,15 +103,34 @@ ENTRY(atomic64_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \ 2: BACKOFF_SPIN(%o2, %o3, 1b); \ ENDPROC(atomic64_##op##_return); -#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) +#define ATOMIC64_FETCH_OP(op) \ +ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \ + BACKOFF_SETUP(%o2); \ +1: ldx [%o1], %g1; \ + op %g1, %o0, %g7; \ + casx [%o1], %g1, %g7; \ + cmp %g1, %g7; \ + bne,pn %xcc, BACKOFF_LABEL(2f, 1b); \ + nop; \ + retl; \ + mov %g1, %o0; \ +2: BACKOFF_SPIN(%o2, %o3, 1b); \ +ENDPROC(atomic64_fetch_##op); + +#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op) ATOMIC64_OPS(add) ATOMIC64_OPS(sub) -ATOMIC64_OP(and) -ATOMIC64_OP(or) -ATOMIC64_OP(xor) #undef ATOMIC64_OPS +#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op) + +ATOMIC64_OPS(and) +ATOMIC64_OPS(or) +ATOMIC64_OPS(xor) + +#undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c index 8eb454cfe05c..de5e97817bdb 100644 --- a/arch/sparc/lib/ksyms.c +++ b/arch/sparc/lib/ksyms.c @@ -107,15 +107,24 @@ EXPORT_SYMBOL(atomic64_##op); EXPORT_SYMBOL(atomic_##op##_return); \ EXPORT_SYMBOL(atomic64_##op##_return); -#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) +#define ATOMIC_FETCH_OP(op) \ +EXPORT_SYMBOL(atomic_fetch_##op); \ +EXPORT_SYMBOL(atomic64_fetch_##op); + +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op) ATOMIC_OPS(add) ATOMIC_OPS(sub) -ATOMIC_OP(and) -ATOMIC_OP(or) -ATOMIC_OP(xor) #undef ATOMIC_OPS +#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) + +ATOMIC_OPS(and) +ATOMIC_OPS(or) +ATOMIC_OPS(xor) + +#undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -- cgit v1.2.3-70-g09d2 From b53d6bedbe781974097fd8c38263f6cc78ff9ea7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:58:25 +0200 Subject: locking/atomic: Remove linux/atomic.h:atomic_fetch_or() Since all architectures have this implemented now natively, remove this dead code. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 2 -- arch/arc/include/asm/atomic.h | 2 -- arch/arm/include/asm/atomic.h | 2 -- arch/arm64/include/asm/atomic.h | 2 -- arch/avr32/include/asm/atomic.h | 2 -- arch/frv/include/asm/atomic.h | 2 -- arch/h8300/include/asm/atomic.h | 2 -- arch/hexagon/include/asm/atomic.h | 2 -- arch/m32r/include/asm/atomic.h | 2 -- arch/m68k/include/asm/atomic.h | 2 -- arch/metag/include/asm/atomic.h | 2 -- arch/mips/include/asm/atomic.h | 2 -- arch/mn10300/include/asm/atomic.h | 2 -- arch/parisc/include/asm/atomic.h | 2 -- arch/s390/include/asm/atomic.h | 2 -- arch/sh/include/asm/atomic.h | 2 -- arch/sparc/include/asm/atomic.h | 1 - arch/sparc/include/asm/atomic_32.h | 2 -- arch/tile/include/asm/atomic.h | 2 -- arch/x86/include/asm/atomic.h | 2 -- arch/xtensa/include/asm/atomic.h | 2 -- include/asm-generic/atomic.h | 2 -- include/linux/atomic.h | 21 --------------------- 23 files changed, 64 deletions(-) (limited to 'arch/sparc') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 8243f17999e3..5377ca8bb503 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -153,8 +153,6 @@ ATOMIC_OPS(sub) #define atomic_andnot atomic_andnot #define atomic64_andnot atomic64_andnot -#define atomic_fetch_or atomic_fetch_or - #undef ATOMIC_OPS #define ATOMIC_OPS(op, asm) \ ATOMIC_OP(op, asm) \ diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index c066a21caaaf..bd9c51cb2bfd 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -189,8 +189,6 @@ ATOMIC_OPS(sub, -=, sub) #define atomic_andnot atomic_andnot -#define atomic_fetch_or atomic_fetch_or - #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ ATOMIC_OP(op, c_op, asm_op) \ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 0feb110ec542..66d0e215a773 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -201,8 +201,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ return val; \ } -#define atomic_fetch_or atomic_fetch_or - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 3128c3d7c1ff..c0235e0ff849 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -128,8 +128,6 @@ #define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot -#define atomic_fetch_or atomic_fetch_or - /* * 64-bit atomic operations. */ diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h index b8681fd495ef..3d5ce38a6f0b 100644 --- a/arch/avr32/include/asm/atomic.h +++ b/arch/avr32/include/asm/atomic.h @@ -66,8 +66,6 @@ ATOMIC_OP_RETURN(add, add, r) ATOMIC_FETCH_OP (sub, sub, rKs21) ATOMIC_FETCH_OP (add, add, r) -#define atomic_fetch_or atomic_fetch_or - #define ATOMIC_OPS(op, asm_op) \ ATOMIC_OP_RETURN(op, asm_op, r) \ static inline void atomic_##op(int i, atomic_t *v) \ diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h index e3e06da0cd59..1c2a5e264fc7 100644 --- a/arch/frv/include/asm/atomic.h +++ b/arch/frv/include/asm/atomic.h @@ -74,8 +74,6 @@ static inline void atomic_dec(atomic_t *v) #define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) #define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_fetch_or atomic_fetch_or - /* * 64-bit atomic ops */ diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 0961b618bdde..349a47a918db 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -54,8 +54,6 @@ static inline void atomic_##op(int i, atomic_t *v) \ ATOMIC_OP_RETURN(add, +=) ATOMIC_OP_RETURN(sub, -=) -#define atomic_fetch_or atomic_fetch_or - #define ATOMIC_OPS(op, c_op) \ ATOMIC_OP(op, c_op) \ ATOMIC_FETCH_OP(op, c_op) diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 07dbb3332b4a..a62ba368b27d 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -152,8 +152,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h index 8ba8a0ab5d5d..640cc1c7099f 100644 --- a/arch/m32r/include/asm/atomic.h +++ b/arch/m32r/include/asm/atomic.h @@ -121,8 +121,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index 5cf9b3b1b6ac..3e03de7ae33b 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -119,8 +119,6 @@ ATOMIC_OPS(sub, -=, sub) ATOMIC_OP(op, c_op, asm_op) \ ATOMIC_FETCH_OP(op, c_op, asm_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, eor) diff --git a/arch/metag/include/asm/atomic.h b/arch/metag/include/asm/atomic.h index 6ca210de8a7d..470e365f04ea 100644 --- a/arch/metag/include/asm/atomic.h +++ b/arch/metag/include/asm/atomic.h @@ -17,8 +17,6 @@ #include #endif -#define atomic_fetch_or atomic_fetch_or - #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic_dec_return(v) atomic_sub_return(1, (v)) diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 431079f8e483..387ce288334e 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -194,8 +194,6 @@ ATOMIC_OPS(sub, -=, subu) ATOMIC_OP(op, c_op, asm_op) \ ATOMIC_FETCH_OP(op, c_op, asm_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, xor) diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h index 3580f789f3a6..36389efd45e8 100644 --- a/arch/mn10300/include/asm/atomic.h +++ b/arch/mn10300/include/asm/atomic.h @@ -113,8 +113,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 29df1f871910..5394b9c5f914 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -148,8 +148,6 @@ ATOMIC_OPS(sub, -=) ATOMIC_OP(op, c_op) \ ATOMIC_FETCH_OP(op, c_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=) ATOMIC_OPS(or, |=) ATOMIC_OPS(xor, ^=) diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 2324e759b544..d28cc2f5b7b2 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -135,8 +135,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ return __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_BARRIER); \ } -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, AND) ATOMIC_OPS(or, OR) ATOMIC_OPS(xor, XOR) diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index d93ed7ce1b2f..c399e1c55685 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -25,8 +25,6 @@ #include #endif -#define atomic_fetch_or atomic_fetch_or - #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) diff --git a/arch/sparc/include/asm/atomic.h b/arch/sparc/include/asm/atomic.h index 1f741bcc73b7..8ff83d8cc33f 100644 --- a/arch/sparc/include/asm/atomic.h +++ b/arch/sparc/include/asm/atomic.h @@ -5,5 +5,4 @@ #else #include #endif -#define atomic_fetch_or atomic_fetch_or #endif diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 5cfb20a599d9..ee3f11c43cda 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -36,8 +36,6 @@ void atomic_set(atomic_t *, int); #define atomic_inc(v) ((void)atomic_add_return( 1, (v))) #define atomic_dec(v) ((void)atomic_add_return( -1, (v))) -#define atomic_fetch_or atomic_fetch_or - #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) #define atomic_xor(i, v) ((void)atomic_fetch_xor((i), (v))) diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h index 9807030557c4..8dda3c8ff5ab 100644 --- a/arch/tile/include/asm/atomic.h +++ b/arch/tile/include/asm/atomic.h @@ -48,8 +48,6 @@ static inline int atomic_read(const atomic_t *v) #define atomic_fetch_sub(i, v) atomic_fetch_add(-(int)(i), (v)) -#define atomic_fetch_or atomic_fetch_or - /** * atomic_sub - subtract integer from atomic variable * @i: integer value to subtract diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 73b8463b89e9..a58b99811105 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -217,8 +217,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OP(op) \ ATOMIC_FETCH_OP(op, c_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &) ATOMIC_OPS(or , |) ATOMIC_OPS(xor, ^) diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index d95a8aa1a6d3..e7a23f2a519a 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -188,8 +188,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index a2304ccf4ed0..9ed8b987185b 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -137,8 +137,6 @@ ATOMIC_FETCH_OP(and, &) #endif #ifndef atomic_fetch_or -#define atomic_fetch_or atomic_fetch_or - ATOMIC_FETCH_OP(or, |) #endif diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 2e6c013ac5a4..0b3802d33125 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -573,27 +573,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif -/** - * atomic_fetch_or - perform *p |= mask and return old value of *p - * @mask: mask to OR on the atomic_t - * @p: pointer to atomic_t - */ -#ifndef atomic_fetch_or -static inline int atomic_fetch_or(int mask, atomic_t *p) -{ - int old, val = atomic_read(p); - - for (;;) { - old = atomic_cmpxchg(p, val, val | mask); - if (old == val) - break; - val = old; - } - - return old; -} -#endif - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif -- cgit v1.2.3-70-g09d2 From 06ee6d571f0e350253a8fc3492316b2be007fae2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 17:39:24 +0900 Subject: genirq: Add affinity hint to irq allocation Add an extra argument to the irq(domain) allocation functions, so we can hand down affinity hints to the allocator. Thats necessary to implement proper support for multiqueue devices. Signed-off-by: Thomas Gleixner Cc: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-4-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- arch/sparc/kernel/irq_64.c | 2 +- arch/x86/kernel/apic/io_apic.c | 5 +++-- include/linux/irq.h | 4 ++-- include/linux/irqdomain.h | 9 ++++++--- kernel/irq/ipi.c | 2 +- kernel/irq/irqdesc.c | 12 ++++++++---- kernel/irq/irqdomain.c | 22 ++++++++++++++-------- kernel/irq/manage.c | 7 ++++--- kernel/irq/msi.c | 3 ++- 9 files changed, 41 insertions(+), 25 deletions(-) (limited to 'arch/sparc') diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e22416ce56ea..34a7930b76ef 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -242,7 +242,7 @@ unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino) { int irq; - irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL); + irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL, NULL); if (irq <= 0) goto out; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 446702ed99dc..7c4f90dd4c2a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -981,7 +981,7 @@ static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, return __irq_domain_alloc_irqs(domain, irq, 1, ioapic_alloc_attr_node(info), - info, legacy); + info, legacy, NULL); } /* @@ -1014,7 +1014,8 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, info->ioapic_pin)) return -ENOMEM; } else { - irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true); + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, + NULL); if (irq >= 0) { irq_data = irq_domain_get_irq_data(domain, irq); data = irq_data->chip_data; diff --git a/include/linux/irq.h b/include/linux/irq.h index f6074813688d..39ce46ac5c18 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -708,11 +708,11 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, - struct module *owner); + struct module *owner, const struct cpumask *affinity); /* use macros to avoid needing export.h for THIS_MODULE */ #define irq_alloc_descs(irq, from, cnt, node) \ - __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE) + __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) #define irq_alloc_desc(node) \ irq_alloc_descs(-1, 0, 1, node) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index f1f36e04d885..1aee0fbe900e 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -39,6 +39,7 @@ struct irq_domain; struct of_device_id; struct irq_chip; struct irq_data; +struct cpumask; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 @@ -217,7 +218,8 @@ extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); extern void irq_set_default_host(struct irq_domain *host); extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, - irq_hw_number_t hwirq, int node); + irq_hw_number_t hwirq, int node, + const struct cpumask *affinity); static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) { @@ -389,7 +391,7 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, - bool realloc); + bool realloc, const struct cpumask *affinity); extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); extern void irq_domain_activate_irq(struct irq_data *irq_data); extern void irq_domain_deactivate_irq(struct irq_data *irq_data); @@ -397,7 +399,8 @@ extern void irq_domain_deactivate_irq(struct irq_data *irq_data); static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs, int node, void *arg) { - return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false); + return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false, + NULL); } extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index 89b49f6773f0..4fd23510d5f2 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -76,7 +76,7 @@ int irq_reserve_ipi(struct irq_domain *domain, } } - virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE); + virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL); if (virq <= 0) { pr_warn("Can't reserve IPI, failed to alloc descs\n"); return -ENOMEM; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8731e1c5d1e7..b8df4fcdbb5f 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -223,7 +223,7 @@ static void free_desc(unsigned int irq) } static int alloc_descs(unsigned int start, unsigned int cnt, int node, - struct module *owner) + const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int i; @@ -333,6 +333,7 @@ static void free_desc(unsigned int irq) } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, + const struct cpumask *affinity, struct module *owner) { u32 i; @@ -453,12 +454,15 @@ EXPORT_SYMBOL_GPL(irq_free_descs); * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) + * @affinity: Optional pointer to an affinity mask which hints where the + * irq descriptors should be allocated and which default + * affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, - struct module *owner) + struct module *owner, const struct cpumask *affinity) { int start, ret; @@ -494,7 +498,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, bitmap_set(allocated_irqs, start, cnt); mutex_unlock(&sparse_irq_lock); - return alloc_descs(start, cnt, node, owner); + return alloc_descs(start, cnt, node, affinity, owner); err: mutex_unlock(&sparse_irq_lock); @@ -512,7 +516,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); */ unsigned int irq_alloc_hwirqs(int cnt, int node) { - int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL); + int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL); if (irq < 0) return 0; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8798b6c9e945..79459b732dc9 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -481,7 +481,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node)); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -835,19 +835,23 @@ const struct irq_domain_ops irq_domain_simple_ops = { EXPORT_SYMBOL_GPL(irq_domain_simple_ops); int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq, - int node) + int node, const struct cpumask *affinity) { unsigned int hint; if (virq >= 0) { - virq = irq_alloc_descs(virq, virq, cnt, node); + virq = __irq_alloc_descs(virq, virq, cnt, node, THIS_MODULE, + affinity); } else { hint = hwirq % nr_irqs; if (hint == 0) hint++; - virq = irq_alloc_descs_from(hint, cnt, node); - if (virq <= 0 && hint > 1) - virq = irq_alloc_descs_from(1, cnt, node); + virq = __irq_alloc_descs(-1, hint, cnt, node, THIS_MODULE, + affinity); + if (virq <= 0 && hint > 1) { + virq = __irq_alloc_descs(-1, 1, cnt, node, THIS_MODULE, + affinity); + } } return virq; @@ -1160,6 +1164,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, * @node: NUMA node id for memory allocation * @arg: domain specific argument * @realloc: IRQ descriptors have already been allocated if true + * @affinity: Optional irq affinity mask for multiqueue devices * * Allocate IRQ numbers and initialized all data structures to support * hierarchy IRQ domains. @@ -1175,7 +1180,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, */ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, - bool realloc) + bool realloc, const struct cpumask *affinity) { int i, ret, virq; @@ -1193,7 +1198,8 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, if (realloc && irq_base >= 0) { virq = irq_base; } else { - virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node); + virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node, + affinity); if (virq < 0) { pr_debug("cannot allocate IRQ(base %d, count %d)\n", irq_base, nr_irqs); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 30658e9827f0..ad0aac6d1248 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -353,10 +353,11 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) return 0; /* - * Preserve an userspace affinity setup, but make sure that - * one of the targets is online. + * Preserve the managed affinity setting and an userspace affinity + * setup, but make sure that one of the targets is online. */ - if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { + if (irqd_affinity_is_managed(&desc->irq_data) || + irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { if (cpumask_intersects(desc->irq_common_data.affinity, cpu_online_mask)) set = desc->irq_common_data.affinity; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index eb5bf2b50b07..58dbbacc6fbb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -334,7 +334,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, ops->set_desc(&arg, desc); virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, - dev_to_node(dev), &arg, false); + dev_to_node(dev), &arg, false, + NULL); if (virq < 0) { ret = -ENOSPC; if (ops->handle_error) -- cgit v1.2.3-70-g09d2