summaryrefslogtreecommitdiff
path: root/include/linux/percpu-defs.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/percpu-defs.h')
-rw-r--r--include/linux/percpu-defs.h99
1 files changed, 45 insertions, 54 deletions
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index af1071535de8..43c854a273c3 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
#endif
-#define PER_CPU_FIRST_SECTION "..first"
#else
#define PER_CPU_SHARED_ALIGNED_SECTION ""
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
#endif
@@ -54,7 +52,7 @@
__section(".discard") __attribute__((unused))
/*
- * s390 and alpha modules require percpu variables to be defined as
+ * alpha modules require percpu variables to be defined as
* weak to force the compiler to generate GOT based external
* references for them. This is necessary because percpu sections
* will be located outside of the usually addressable area.
@@ -65,14 +63,15 @@
* 1. The symbol must be globally unique, even the static ones.
* 2. Static percpu variables cannot be defined inside a function.
*
- * Archs which need weak percpu definitions should define
- * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
+ * Archs which need weak percpu definitions should set
+ * CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU when necessary.
*
* To ensure that the generic code observes the above two
* restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak
* definition is used for all cases.
*/
-#if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
+#if (defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)) || \
+ defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
/*
* __pcpu_scope_* dummy variable is used to enforce scope. It
* receives the static modifier when it's used in front of
@@ -115,14 +114,17 @@
DEFINE_PER_CPU_SECTION(type, name, "")
/*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
+ * Declaration/definition used for per-CPU variables that are frequently
+ * accessed and should be in a single cacheline.
+ *
+ * For use only by architecture and core code. Only use scalar or pointer
+ * types to maximize density.
*/
-#define DECLARE_PER_CPU_FIRST(type, name) \
- DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DECLARE_PER_CPU_CACHE_HOT(type, name) \
+ DECLARE_PER_CPU_SECTION(type, name, "..hot.." #name)
-#define DEFINE_PER_CPU_FIRST(type, name) \
- DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DEFINE_PER_CPU_CACHE_HOT(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, "..hot.." #name)
/*
* Declaration/definition used for per-CPU variables that must be cacheline
@@ -220,15 +222,17 @@ do { \
(void)__vpp_verify; \
} while (0)
+#define PERCPU_PTR(__p) \
+ (TYPEOF_UNQUAL(*(__p)) __force __kernel *)((__force unsigned long)(__p))
+
#ifdef CONFIG_SMP
/*
- * Add an offset to a pointer but keep the pointer as-is. Use RELOC_HIDE()
- * to prevent the compiler from making incorrect assumptions about the
- * pointer value. The weird cast keeps both GCC and sparse happy.
+ * Add an offset to a pointer. Use RELOC_HIDE() to prevent the compiler
+ * from making incorrect assumptions about the pointer value.
*/
#define SHIFT_PERCPU_PTR(__p, __offset) \
- RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset))
+ RELOC_HIDE(PERCPU_PTR(__p), (__offset))
#define per_cpu_ptr(ptr, cpu) \
({ \
@@ -254,13 +258,13 @@ do { \
#else /* CONFIG_SMP */
-#define VERIFY_PERCPU_PTR(__p) \
+#define per_cpu_ptr(ptr, cpu) \
({ \
- __verify_pcpu_ptr(__p); \
- (typeof(*(__p)) __kernel __force *)(__p); \
+ (void)(cpu); \
+ __verify_pcpu_ptr(ptr); \
+ PERCPU_PTR(ptr); \
})
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR(ptr); })
#define raw_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
@@ -310,12 +314,12 @@ extern void __bad_size_call_parameter(void);
#ifdef CONFIG_DEBUG_PREEMPT
extern void __this_cpu_preempt_check(const char *op);
#else
-static inline void __this_cpu_preempt_check(const char *op) { }
+static __always_inline void __this_cpu_preempt_check(const char *op) { }
#endif
#define __pcpu_size_call_return(stem, variable) \
({ \
- typeof(variable) pscr_ret__; \
+ TYPEOF_UNQUAL(variable) pscr_ret__; \
__verify_pcpu_ptr(&(variable)); \
switch(sizeof(variable)) { \
case 1: pscr_ret__ = stem##1(variable); break; \
@@ -330,7 +334,7 @@ static inline void __this_cpu_preempt_check(const char *op) { }
#define __pcpu_size_call_return2(stem, variable, ...) \
({ \
- typeof(variable) pscr2_ret__; \
+ TYPEOF_UNQUAL(variable) pscr2_ret__; \
__verify_pcpu_ptr(&(variable)); \
switch(sizeof(variable)) { \
case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \
@@ -343,31 +347,19 @@ static inline void __this_cpu_preempt_check(const char *op) { }
pscr2_ret__; \
})
-/*
- * Special handling for cmpxchg_double. cmpxchg_double is passed two
- * percpu variables. The first has to be aligned to a double word
- * boundary and the second has to follow directly thereafter.
- * We enforce this on all architectures even if they don't support
- * a double cmpxchg instruction, since it's a cheap requirement, and it
- * avoids breaking the requirement for architectures with the instruction.
- */
-#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...) \
+#define __pcpu_size_call_return2bool(stem, variable, ...) \
({ \
- bool pdcrb_ret__; \
- __verify_pcpu_ptr(&(pcp1)); \
- BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2)); \
- VM_BUG_ON((unsigned long)(&(pcp1)) % (2 * sizeof(pcp1))); \
- VM_BUG_ON((unsigned long)(&(pcp2)) != \
- (unsigned long)(&(pcp1)) + sizeof(pcp1)); \
- switch(sizeof(pcp1)) { \
- case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break; \
- case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break; \
- case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break; \
- case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break; \
+ bool pscr2_ret__; \
+ __verify_pcpu_ptr(&(variable)); \
+ switch(sizeof(variable)) { \
+ case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \
+ case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \
+ case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \
+ case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \
default: \
__bad_size_call_parameter(); break; \
} \
- pdcrb_ret__; \
+ pscr2_ret__; \
})
#define __pcpu_size_call(stem, variable, ...) \
@@ -384,7 +376,7 @@ do { \
} while (0)
/*
- * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com>
+ * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@gentwo.org>
*
* Optimized manipulation for memory allocated through the per cpu
* allocator or for addresses of per cpu variables.
@@ -426,9 +418,8 @@ do { \
#define raw_cpu_xchg(pcp, nval) __pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval)
#define raw_cpu_cmpxchg(pcp, oval, nval) \
__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
-#define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
- __pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
-
+#define raw_cpu_try_cmpxchg(pcp, ovalp, nval) \
+ __pcpu_size_call_return2bool(raw_cpu_try_cmpxchg_, pcp, ovalp, nval)
#define raw_cpu_sub(pcp, val) raw_cpu_add(pcp, -(val))
#define raw_cpu_inc(pcp) raw_cpu_add(pcp, 1)
#define raw_cpu_dec(pcp) raw_cpu_sub(pcp, 1)
@@ -488,9 +479,10 @@ do { \
raw_cpu_cmpxchg(pcp, oval, nval); \
})
-#define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
-({ __this_cpu_preempt_check("cmpxchg_double"); \
- raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2); \
+#define __this_cpu_try_cmpxchg(pcp, ovalp, nval) \
+({ \
+ __this_cpu_preempt_check("try_cmpxchg"); \
+ raw_cpu_try_cmpxchg(pcp, ovalp, nval); \
})
#define __this_cpu_sub(pcp, val) __this_cpu_add(pcp, -(typeof(pcp))(val))
@@ -513,9 +505,8 @@ do { \
#define this_cpu_xchg(pcp, nval) __pcpu_size_call_return2(this_cpu_xchg_, pcp, nval)
#define this_cpu_cmpxchg(pcp, oval, nval) \
__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
-#define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
- __pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
-
+#define this_cpu_try_cmpxchg(pcp, ovalp, nval) \
+ __pcpu_size_call_return2bool(this_cpu_try_cmpxchg_, pcp, ovalp, nval)
#define this_cpu_sub(pcp, val) this_cpu_add(pcp, -(typeof(pcp))(val))
#define this_cpu_inc(pcp) this_cpu_add(pcp, 1)
#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1)
generated by cgit (git 2.34.1) at 2025-12-21 20:58:40 +0000