--- zzzz-none-000/linux-3.10.107/Documentation/static-keys.txt 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/Documentation/static-keys.txt 2021-02-04 17:41:59.000000000 +0000 @@ -1,7 +1,22 @@ Static Keys ----------- -By: Jason Baron +DEPRECATED API: + +The use of 'struct static_key' directly, is now DEPRECATED. In addition +static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: + +struct static_key false = STATIC_KEY_INIT_FALSE; +struct static_key true = STATIC_KEY_INIT_TRUE; +static_key_true() +static_key_false() + +The updated API replacements are: + +DEFINE_STATIC_KEY_TRUE(key); +DEFINE_STATIC_KEY_FALSE(key); +static_branch_likely() +static_branch_unlikely() 0) Abstract @@ -9,22 +24,22 @@ performance-sensitive fast-path kernel code, via a GCC feature and a code patching technique. A quick example: - struct static_key key = STATIC_KEY_INIT_FALSE; + DEFINE_STATIC_KEY_FALSE(key); ... - if (static_key_false(&key)) + if (static_branch_unlikely(&key)) do unlikely code else do likely code ... - static_key_slow_inc(); + static_branch_enable(&key); ... - static_key_slow_inc(); + static_branch_disable(&key); ... -The static_key_false() branch will be generated into the code with as little +The static_branch_unlikely() branch will be generated into the code with as little impact to the likely code path as possible. @@ -56,7 +71,7 @@ For example, if we have a simple branch that is disabled by default: - if (static_key_false(&key)) + if (static_branch_unlikely(&key)) printk("I am the true branch\n"); Thus, by default the 'printk' will not be emitted. And the code generated will @@ -75,68 +90,55 @@ In order to make use of this optimization you must first define a key: - struct static_key key; - -Which is initialized as: - - struct static_key key = STATIC_KEY_INIT_TRUE; + DEFINE_STATIC_KEY_TRUE(key); or: - struct static_key key = STATIC_KEY_INIT_FALSE; + DEFINE_STATIC_KEY_FALSE(key); + -If the key is not initialized, it is default false. The 'struct static_key', -must be a 'global'. That is, it can't be allocated on the stack or dynamically +The key must be global, that is, it can't be allocated on the stack or dynamically allocated at run-time. The key is then used in code as: - if (static_key_false(&key)) + if (static_branch_unlikely(&key)) do unlikely code else do likely code Or: - if (static_key_true(&key)) + if (static_branch_likely(&key)) do likely code else do unlikely code -A key that is initialized via 'STATIC_KEY_INIT_FALSE', must be used in a -'static_key_false()' construct. Likewise, a key initialized via -'STATIC_KEY_INIT_TRUE' must be used in a 'static_key_true()' construct. A -single key can be used in many branches, but all the branches must match the -way that the key has been initialized. +Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may +be used in either static_branch_likely() or static_branch_unlikely() +statemnts. -The branch(es) can then be switched via: +Branch(es) can be set true via: - static_key_slow_inc(&key); +static_branch_enable(&key); + +or false via: + +static_branch_disable(&key); + +The branch(es) can then be switched via reference counts: + + static_branch_inc(&key); ... - static_key_slow_dec(&key); + static_branch_dec(&key); -Thus, 'static_key_slow_inc()' means 'make the branch true', and -'static_key_slow_dec()' means 'make the the branch false' with appropriate +Thus, 'static_branch_inc()' means 'make the branch true', and +'static_branch_dec()' means 'make the branch false' with appropriate reference counting. For example, if the key is initialized true, a -static_key_slow_dec(), will switch the branch to false. And a subsequent -static_key_slow_inc(), will change the branch back to true. Likewise, if the -key is initialized false, a 'static_key_slow_inc()', will change the branch to -true. And then a 'static_key_slow_dec()', will again make the branch false. - -An example usage in the kernel is the implementation of tracepoints: - - static inline void trace_##name(proto) \ - { \ - if (static_key_false(&__tracepoint_##name.key)) \ - __DO_TRACE(&__tracepoint_##name, \ - TP_PROTO(data_proto), \ - TP_ARGS(data_args), \ - TP_CONDITION(cond)); \ - } - -Tracepoints are disabled by default, and can be placed in performance critical -pieces of the kernel. Thus, by using a static key, the tracepoints can have -absolutely minimal impact when not in use. +static_branch_dec(), will switch the branch to false. And a subsequent +static_branch_inc(), will change the branch back to true. Likewise, if the +key is initialized false, a 'static_branch_inc()', will change the branch to +true. And then a 'static_branch_dec()', will again make the branch false. 4) Architecture level code patching interface, 'jump labels' @@ -150,9 +152,12 @@ * #define JUMP_LABEL_NOP_SIZE, see: arch/x86/include/asm/jump_label.h -* __always_inline bool arch_static_branch(struct static_key *key), see: +* __always_inline bool arch_static_branch(struct static_key *key, bool branch), see: arch/x86/include/asm/jump_label.h +* __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch), + see: arch/x86/include/asm/jump_label.h + * void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type), see: arch/x86/kernel/jump_label.c @@ -173,7 +178,7 @@ { int pid; -+ if (static_key_false(&key)) ++ if (static_branch_unlikely(&key)) + printk("I am the true branch\n"); rcu_read_lock(); @@ -236,7 +241,7 @@ If we then include the padding bytes, the jump label code saves, 16 total bytes of instruction memory for this small function. In this case the non-jump label -function is 80 bytes long. Thus, we have have saved 20% of the instruction +function is 80 bytes long. Thus, we have saved 20% of the instruction footprint. We can in fact improve this even further, since the 5-byte no-op really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp. However, we have not yet implemented optimal no-op sizes (they are currently