From afbe7973173a7ce0a68af8b33e44c967582297be Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 24 Sep 2020 12:30:20 -0400 Subject: tracepoints: Add helper to test if tracepoint is enabled in a header As tracepoints are discouraged from being added in a header because it can cause side effects if other tracepoints are in headers, as well as bloat the kernel as the trace_() function is not a small inline, the common workaround is to add a function call that calls a wrapper function in a C file that then calls the tracepoint. But as function calls add overhead, this function should only be called when the tracepoint in question is enabled. To get around this overhead, a static_branch can be used to only have the tracepoint wrapper get called when the tracepoint is enabled. Add a tracepoint_enabled(tp) macro that gets passed the name of the tracepoint, and this becomes a static_branch that is enabled when the tracepoint is enabled and is a nop when the tracepoint is disabled. Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint-defs.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index b29950a19205..60625973faaf 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -48,4 +48,38 @@ struct bpf_raw_event_map { u32 writable_size; } __aligned(32); +/* + * If a tracepoint needs to be called from a header file, it is not + * recommended to call it directly, as tracepoints in header files + * may cause side-effects and bloat the kernel. Instead, use + * tracepoint_enabled() to test if the tracepoint is enabled, then if + * it is, call a wrapper function defined in a C file that will then + * call the tracepoint. + * + * For "trace_foo_bar()", you would need to create a wrapper function + * in a C file to call trace_foo_bar(): + * void do_trace_foo_bar(args) { trace_foo_bar(args); } + * Then in the header file, declare the tracepoint: + * DECLARE_TRACEPOINT(foo_bar); + * And call your wrapper: + * static inline void some_inlined_function() { + * [..] + * if (tracepoint_enabled(foo_bar)) + * do_trace_foo_bar(args); + * [..] + * } + * + * Note: tracepoint_enabled(foo_bar) is equivalent to trace_foo_bar_enabled() + * but is safe to have in headers, where trace_foo_bar_enabled() is not. + */ +#define DECLARE_TRACEPOINT(tp) \ + extern struct tracepoint __tracepoint_##tp + +#ifdef CONFIG_TRACEPOINTS +# define tracepoint_enabled(tp) \ + static_key_false(&(__tracepoint_##tp).key) +#else +# define tracepoint_enabled(tracepoint) false +#endif + #endif -- cgit v1.2.3 From c65fc2276f0f022f5ad4a84658add2b28cff7227 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 24 Sep 2020 12:43:46 -0400 Subject: mm/page_ref: Convert the open coded tracepoint enabled to the new helper As more use cases of checking if a tracepoint is enabled in a header are coming to fruition, a helper macro, tracepoint_enabled(), has been added to check if a tracepoint is enabled or not, and can be used with minimal header requirements (avoid "include hell"). Convert the page_ref logic over to the new helper macro. Cc: Joonsoo Kim Cc: Michal Nazarewicz Cc: Vlastimil Babka Cc: Minchan Kim Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Sergey Senozhatsky Cc: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- include/linux/page_ref.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index d27701199a4d..f3318f34fc54 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -7,13 +7,13 @@ #include #include -extern struct tracepoint __tracepoint_page_ref_set; -extern struct tracepoint __tracepoint_page_ref_mod; -extern struct tracepoint __tracepoint_page_ref_mod_and_test; -extern struct tracepoint __tracepoint_page_ref_mod_and_return; -extern struct tracepoint __tracepoint_page_ref_mod_unless; -extern struct tracepoint __tracepoint_page_ref_freeze; -extern struct tracepoint __tracepoint_page_ref_unfreeze; +DECLARE_TRACEPOINT(page_ref_set); +DECLARE_TRACEPOINT(page_ref_mod); +DECLARE_TRACEPOINT(page_ref_mod_and_test); +DECLARE_TRACEPOINT(page_ref_mod_and_return); +DECLARE_TRACEPOINT(page_ref_mod_unless); +DECLARE_TRACEPOINT(page_ref_freeze); +DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF @@ -24,7 +24,7 @@ extern struct tracepoint __tracepoint_page_ref_unfreeze; * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ -#define page_ref_tracepoint_active(t) static_key_false(&(t).key) +#define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); @@ -75,7 +75,7 @@ static inline int page_count(struct page *page) static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); - if (page_ref_tracepoint_active(__tracepoint_page_ref_set)) + if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } @@ -91,14 +91,14 @@ static inline void init_page_count(struct page *page) static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } @@ -106,7 +106,7 @@ static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -nr, ret); return ret; } @@ -114,14 +114,14 @@ static inline int page_ref_sub_return(struct page *page, int nr) static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) + if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } @@ -129,7 +129,7 @@ static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } @@ -138,7 +138,7 @@ static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } @@ -147,7 +147,7 @@ static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) + if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } @@ -156,7 +156,7 @@ static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } @@ -165,7 +165,7 @@ static inline int page_ref_add_unless(struct page *page, int nr, int u) { int ret = atomic_add_unless(&page->_refcount, nr, u); - if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless)) + if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } @@ -174,7 +174,7 @@ static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); - if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze)) + if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } @@ -185,7 +185,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); - if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) + if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } -- cgit v1.2.3 From 02dae28f0b542969e44cbc1e14ffc9944cd2975c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 31 Aug 2020 11:11:01 +0800 Subject: ftrace: Simplify the dyn_ftrace->flags macro All the three macro are defined to be used for ftrace_rec_count(). This can be achieved by (flags & FTRACE_REF_MAX) directly. Since no other places would use those macros, remove them for clarity. Also it fixes a typo in the comment. Link: https://lkml.kernel.org/r/20200831031104.23322-4-richard.weiyang@linux.alibaba.com Signed-off-by: Wei Yang Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5c2d5cc6e6a..b1f56e3410dc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -432,7 +432,7 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * * When a new ftrace_ops is registered and wants a function to save - * pt_regs, the rec->flag REGS is set. When the function has been + * pt_regs, the rec->flags REGS is set. When the function has been * set up to save regs, the REG_EN flag is set. Once a function * starts saving regs it will do so until all ftrace_ops are removed * from tracing that function. @@ -450,12 +450,9 @@ enum { }; #define FTRACE_REF_MAX_SHIFT 23 -#define FTRACE_FL_BITS 9 -#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) -#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) -#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK) +#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) struct dyn_ftrace { unsigned long ip; /* address of mcount call-site */ -- cgit v1.2.3 From 40dc4a42b97ef5a52ef34a73093a7992faaab15e Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 31 Aug 2020 11:11:04 +0800 Subject: ftrace: ftrace_global_list is renamed to ftrace_ops_list Fix the comment to comply with the code. Link: https://lkml.kernel.org/r/20200831031104.23322-7-richard.weiyang@linux.alibaba.com Signed-off-by: Wei Yang Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b1f56e3410dc..1bd3a0356ae4 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -217,11 +217,11 @@ extern struct ftrace_ops __rcu *ftrace_ops_list; extern struct ftrace_ops ftrace_list_end; /* - * Traverse the ftrace_global_list, invoking all entries. The reason that we + * Traverse the ftrace_ops_list, invoking all entries. The reason that we * can use rcu_dereference_raw_check() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw_check() calls are needed to handle - * concurrent insertions into the ftrace_global_list. + * concurrent insertions into the ftrace_ops_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -- cgit v1.2.3