diff options
Diffstat (limited to 'include/linux/percpu-defs.h')
| -rw-r--r-- | include/linux/percpu-defs.h | 409 |
1 files changed, 382 insertions, 27 deletions
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 27ef6b190ea6..43c854a273c3 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -1,6 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/percpu-defs.h - basic definitions for percpu areas + * + * DO NOT INCLUDE DIRECTLY OUTSIDE PERCPU IMPLEMENTATION PROPER. + * + * This file is separate from linux/percpu.h to avoid cyclic inclusion + * dependency from arch header files. Only to be included from + * asm/percpu.h. + * + * This file includes macros necessary to declare percpu sections and + * variables, and definitions of percpu accessors and operations. It + * should provide enough percpu features to arch header files even when + * they can only include asm/percpu.h to avoid cyclic inclusion dependency. + */ + #ifndef _LINUX_PERCPU_DEFS_H #define _LINUX_PERCPU_DEFS_H +#ifdef CONFIG_SMP + +#ifdef MODULE +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_ALIGNED_SECTION "" +#else +#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned" +#define PER_CPU_ALIGNED_SECTION "..shared_aligned" +#endif + +#else + +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_ALIGNED_SECTION "..shared_aligned" + +#endif + /* * Base implementations of per-CPU variable declarations and definitions, where * the section in which the variable is to be placed is provided by the @@ -16,20 +49,10 @@ PER_CPU_ATTRIBUTES #define __PCPU_DUMMY_ATTRS \ - __attribute__((section(".discard"), unused)) - -/* - * Macro which verifies @ptr is a percpu pointer without evaluating - * @ptr. This is to be used in percpu accessors to verify that the - * input parameter is a percpu pointer. - */ -#define __verify_pcpu_ptr(ptr) do { \ - const void __percpu *__vpp_verify = (typeof(ptr))NULL; \ - (void)__vpp_verify; \ -} while (0) + __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. @@ -40,14 +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 @@ -66,8 +90,8 @@ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ - __typeof__(type) name + extern __PCPU_ATTRS(sec) __typeof__(type) name; \ + __PCPU_ATTRS(sec) __weak __typeof__(type) name #else /* * Normal declaration and definition macros. @@ -76,8 +100,7 @@ extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ - __typeof__(type) name + __PCPU_ATTRS(sec) __typeof__(type) name #endif /* @@ -91,14 +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 @@ -142,10 +168,24 @@ * Declaration/definition used for per-CPU variables that must be read mostly. */ #define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ - DECLARE_PER_CPU_SECTION(type, name, "..readmostly") + DECLARE_PER_CPU_SECTION(type, name, "..read_mostly") #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ - DEFINE_PER_CPU_SECTION(type, name, "..readmostly") + DEFINE_PER_CPU_SECTION(type, name, "..read_mostly") + +/* + * Declaration/definition used for per-CPU variables that should be accessed + * as decrypted when memory encryption is enabled in the guest. + */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define DECLARE_PER_CPU_DECRYPTED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, "..decrypted") + +#define DEFINE_PER_CPU_DECRYPTED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, "..decrypted") +#else +#define DEFINE_PER_CPU_DECRYPTED(type, name) DEFINE_PER_CPU(type, name) +#endif /* * Intermodule exports for per-CPU variables. sparse forgets about @@ -160,4 +200,319 @@ #define EXPORT_PER_CPU_SYMBOL_GPL(var) #endif +/* + * Accessors and operations. + */ +#ifndef __ASSEMBLY__ + +/* + * __verify_pcpu_ptr() verifies @ptr is a percpu pointer without evaluating + * @ptr and is invoked once before a percpu area is accessed by all + * accessors and operations. This is performed in the generic part of + * percpu and arch overrides don't need to worry about it; however, if an + * arch wants to implement an arch-specific percpu accessor or operation, + * it may use __verify_pcpu_ptr() to verify the parameters. + * + * + 0 is required in order to convert the pointer type from a + * potential array type to a pointer to a single item of the array. + */ +#define __verify_pcpu_ptr(ptr) \ +do { \ + const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ + (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. Use RELOC_HIDE() to prevent the compiler + * from making incorrect assumptions about the pointer value. + */ +#define SHIFT_PERCPU_PTR(__p, __offset) \ + RELOC_HIDE(PERCPU_PTR(__p), (__offset)) + +#define per_cpu_ptr(ptr, cpu) \ +({ \ + __verify_pcpu_ptr(ptr); \ + SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))); \ +}) + +#define raw_cpu_ptr(ptr) \ +({ \ + __verify_pcpu_ptr(ptr); \ + arch_raw_cpu_ptr(ptr); \ +}) + +#ifdef CONFIG_DEBUG_PREEMPT +#define this_cpu_ptr(ptr) \ +({ \ + __verify_pcpu_ptr(ptr); \ + SHIFT_PERCPU_PTR(ptr, my_cpu_offset); \ +}) +#else +#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) +#endif + +#else /* CONFIG_SMP */ + +#define per_cpu_ptr(ptr, cpu) \ +({ \ + (void)(cpu); \ + __verify_pcpu_ptr(ptr); \ + PERCPU_PTR(ptr); \ +}) + +#define raw_cpu_ptr(ptr) per_cpu_ptr(ptr, 0) +#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) + +#endif /* CONFIG_SMP */ + +#define per_cpu(var, cpu) (*per_cpu_ptr(&(var), cpu)) + +/* + * Must be an lvalue. Since @var must be a simple identifier, + * we force a syntax error here if it isn't. + */ +#define get_cpu_var(var) \ +(*({ \ + preempt_disable(); \ + this_cpu_ptr(&var); \ +})) + +/* + * The weird & is necessary because sparse considers (void)(var) to be + * a direct dereference of percpu variable (var). + */ +#define put_cpu_var(var) \ +do { \ + (void)&(var); \ + preempt_enable(); \ +} while (0) + +#define get_cpu_ptr(var) \ +({ \ + preempt_disable(); \ + this_cpu_ptr(var); \ +}) + +#define put_cpu_ptr(var) \ +do { \ + (void)(var); \ + preempt_enable(); \ +} while (0) + +/* + * Branching function to split up a function into a set of functions that + * are called for different scalar sizes of the objects handled. + */ + +extern void __bad_size_call_parameter(void); + +#ifdef CONFIG_DEBUG_PREEMPT +extern void __this_cpu_preempt_check(const char *op); +#else +static __always_inline void __this_cpu_preempt_check(const char *op) { } +#endif + +#define __pcpu_size_call_return(stem, variable) \ +({ \ + TYPEOF_UNQUAL(variable) pscr_ret__; \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: pscr_ret__ = stem##1(variable); break; \ + case 2: pscr_ret__ = stem##2(variable); break; \ + case 4: pscr_ret__ = stem##4(variable); break; \ + case 8: pscr_ret__ = stem##8(variable); break; \ + default: \ + __bad_size_call_parameter(); break; \ + } \ + pscr_ret__; \ +}) + +#define __pcpu_size_call_return2(stem, variable, ...) \ +({ \ + TYPEOF_UNQUAL(variable) 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; \ + } \ + pscr2_ret__; \ +}) + +#define __pcpu_size_call_return2bool(stem, variable, ...) \ +({ \ + 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; \ + } \ + pscr2_ret__; \ +}) + +#define __pcpu_size_call(stem, variable, ...) \ +do { \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: stem##1(variable, __VA_ARGS__);break; \ + case 2: stem##2(variable, __VA_ARGS__);break; \ + case 4: stem##4(variable, __VA_ARGS__);break; \ + case 8: stem##8(variable, __VA_ARGS__);break; \ + default: \ + __bad_size_call_parameter();break; \ + } \ +} while (0) + +/* + * 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. + * + * These operation guarantee exclusivity of access for other operations + * on the *same* processor. The assumption is that per cpu data is only + * accessed by a single processor instance (the current one). + * + * The arch code can provide optimized implementation by defining macros + * for certain scalar sizes. F.e. provide this_cpu_add_2() to provide per + * cpu atomic operations for 2 byte sized RMW actions. If arch code does + * not provide operations for a scalar size then the fallback in the + * generic code will be used. + * + * cmpxchg_double replaces two adjacent scalars at once. The first two + * parameters are per cpu variables which have to be of the same size. A + * truth value is returned to indicate success or failure (since a double + * register result is difficult to handle). There is very limited hardware + * support for these operations, so only certain sizes may work. + */ + +/* + * Operations for contexts where we do not want to do any checks for + * preemptions. Unless strictly necessary, always use [__]this_cpu_*() + * instead. + * + * If there is no other protection through preempt disable and/or disabling + * interrupts then one of these RMW operations can show unexpected behavior + * because the execution thread was rescheduled on another processor or an + * interrupt occurred and the same percpu variable was modified from the + * interrupt context. + */ +#define raw_cpu_read(pcp) __pcpu_size_call_return(raw_cpu_read_, pcp) +#define raw_cpu_write(pcp, val) __pcpu_size_call(raw_cpu_write_, pcp, val) +#define raw_cpu_add(pcp, val) __pcpu_size_call(raw_cpu_add_, pcp, val) +#define raw_cpu_and(pcp, val) __pcpu_size_call(raw_cpu_and_, pcp, val) +#define raw_cpu_or(pcp, val) __pcpu_size_call(raw_cpu_or_, pcp, val) +#define raw_cpu_add_return(pcp, val) __pcpu_size_call_return2(raw_cpu_add_return_, pcp, val) +#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_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) +#define raw_cpu_sub_return(pcp, val) raw_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define raw_cpu_inc_return(pcp) raw_cpu_add_return(pcp, 1) +#define raw_cpu_dec_return(pcp) raw_cpu_add_return(pcp, -1) + +/* + * Operations for contexts that are safe from preemption/interrupts. These + * operations verify that preemption is disabled. + */ +#define __this_cpu_read(pcp) \ +({ \ + __this_cpu_preempt_check("read"); \ + raw_cpu_read(pcp); \ +}) + +#define __this_cpu_write(pcp, val) \ +({ \ + __this_cpu_preempt_check("write"); \ + raw_cpu_write(pcp, val); \ +}) + +#define __this_cpu_add(pcp, val) \ +({ \ + __this_cpu_preempt_check("add"); \ + raw_cpu_add(pcp, val); \ +}) + +#define __this_cpu_and(pcp, val) \ +({ \ + __this_cpu_preempt_check("and"); \ + raw_cpu_and(pcp, val); \ +}) + +#define __this_cpu_or(pcp, val) \ +({ \ + __this_cpu_preempt_check("or"); \ + raw_cpu_or(pcp, val); \ +}) + +#define __this_cpu_add_return(pcp, val) \ +({ \ + __this_cpu_preempt_check("add_return"); \ + raw_cpu_add_return(pcp, val); \ +}) + +#define __this_cpu_xchg(pcp, nval) \ +({ \ + __this_cpu_preempt_check("xchg"); \ + raw_cpu_xchg(pcp, nval); \ +}) + +#define __this_cpu_cmpxchg(pcp, oval, nval) \ +({ \ + __this_cpu_preempt_check("cmpxchg"); \ + raw_cpu_cmpxchg(pcp, oval, nval); \ +}) + +#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)) +#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) +#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) +#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) + +/* + * Operations with implied preemption/interrupt protection. These + * operations can be used without worrying about preemption or interrupt. + */ +#define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, pcp) +#define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, pcp, val) +#define this_cpu_add(pcp, val) __pcpu_size_call(this_cpu_add_, pcp, val) +#define this_cpu_and(pcp, val) __pcpu_size_call(this_cpu_and_, pcp, val) +#define this_cpu_or(pcp, val) __pcpu_size_call(this_cpu_or_, pcp, val) +#define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +#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_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) +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) +#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) + +#endif /* __ASSEMBLY__ */ #endif /* _LINUX_PERCPU_DEFS_H */ |