From e6a8791b1f24fc46d9b0bdd02a5b2bdbceeff8ad Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 20 Mar 2023 15:03:37 -0300 Subject: [PATCH] this_cpu_cmpxchg: x86: switch this_cpu_cmpxchg to locked, add _local function Goal is to have vmstat_shepherd to transfer from per-CPU counters to global counters remotely. For this, an atomic this_cpu_cmpxchg is necessary. Following the kernel convention for cmpxchg/cmpxchg_local, change x86's this_cpu_cmpxchg_ helpers to be atomic. and add this_cpu_cmpxchg_local_ helpers which are not atomic. Link: https://lkml.kernel.org/r/20230320180745.658574087@redhat.com Signed-off-by: Marcelo Tosatti Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Michal Hocko Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- arch/x86/include/asm/percpu.h | 41 ++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 13c0d63ed55e4..bae00203c08f4 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -197,11 +197,11 @@ do { \ * cmpxchg has no such implied lock semantics as a result it is much * more efficient for cpu local operations. */ -#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval) \ +#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval, lockp) \ ({ \ __pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval); \ __pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \ - asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \ + asm qual (__pcpu_op2_##size(lockp "cmpxchg", "%[nval]", \ __percpu_arg([var])) \ : [oval] "+a" (pco_old__), \ [var] "+m" (_var) \ @@ -279,16 +279,20 @@ do { \ #define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val) #define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val) #define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(4, , pcp, val) -#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval) -#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval) -#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval) +#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval, "") +#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval, "") +#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval, "") #define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val) #define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val) #define this_cpu_add_return_4(pcp, val) percpu_add_return_op(4, volatile, pcp, val) -#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval) -#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval) -#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval) +#define this_cpu_cmpxchg_local_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval, "") +#define this_cpu_cmpxchg_local_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval, "") +#define this_cpu_cmpxchg_local_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval, "") + +#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval, LOCK_PREFIX) +#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval, LOCK_PREFIX) +#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval, LOCK_PREFIX) #ifdef CONFIG_X86_CMPXCHG64 #define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2) \ @@ -319,16 +323,17 @@ do { \ #define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val) #define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val) #define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval) -#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval) - -#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) -#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) -#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val) -#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val) -#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val) -#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val) -#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval) -#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval) +#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval, "") + +#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) +#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) +#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val) +#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val) +#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val) +#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val) +#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval) +#define this_cpu_cmpxchg_local_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval, "") +#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval, LOCK_PREFIX) /* * Pretty complex macro to generate cmpxchg16 instruction. The instruction -- 2.50.1