tracing: gfp: Updates for 6.14
Subsystems (3)
Steven Rostedt
maintainercover tracing: gfp: Updates for 6.14
Head SHA1: 4fc86cbb2d24860b019227ec1d5b38dd0ee7cedf
Steven Rostedt (2):
fgraph: Remove calltime and rettime from generic operations
tracing: gfp: Remove duplication of recording GFP flags
----
include/linux/ftrace.h | 2 -- include/trace/events/mmflags.h | 41 +++++++++--------------------------- kernel/trace/fgraph.c | 1 - kernel/trace/trace.h | 4 +++- kernel/trace/trace_entries.h | 8 +++---- kernel/trace/trace_functions_graph.c | 33 +++++++++++++++++------------ kernel/trace/trace_irqsoff.c | 5 +++-- kernel/trace/trace_sched_wakeup.c | 6 ++++-- 8 files changed, 43 insertions(+), 57 deletions(-)
Steven Rostedt
maintainerPATCH 1/2 fgraph: Remove calltime and rettime from generic operations
From: Steven Rostedt <[email protected]>
The function graph infrastructure is now generic so that kretprobes, fprobes and BPF can use it. But there is still some leftover logic that only the function graph tracer itself uses. This is the calculation of the calltime and return time of the functions. The calculation of the calltime has been moved into the function graph tracer and those users that need it so that it doesn't cause overhead to the other users. But the return function timestamp was still called.
Instead of just moving the taking of the timestamp into the function graph trace remove the calltime and rettime completely from the ftrace_graph_ret structure. Instead, move it into the function graph return entry event structure and this also moves all the calltime and rettime logic out of the generic fgraph.c code and into the tracing code that uses it.
This has been reported to decrease the overhead by ~27%.
--- include/linux/ftrace.h | 2 -- kernel/trace/fgraph.c | 1 - kernel/trace/trace.h | 4 +++- kernel/trace/trace_entries.h | 8 +++---- kernel/trace/trace_functions_graph.c | 33 ++++++++++++++++------------ kernel/trace/trace_irqsoff.c | 5 +++-- kernel/trace/trace_sched_wakeup.c | 6 +++-- 7 files changed, 33 insertions(+), 26 deletions(-)
include/linux/ftrace.h +0 -2
@@ -1061,8 +1061,6 @@ struct ftrace_graph_ret {int depth;/* Number of functions that overran the depth limit for current task */ unsigned int overrun; -unsigned long long calltime; -unsigned long long rettime; } __packed;struct fgraph_ops ;
kernel/trace/fgraph.c +0 -1
@@ -818,7 +818,6 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regsreturn (unsigned long )panic; } - trace.rettime =trace_clock_local ();#ifdef CONFIG_FUNCTION_GRAPH_RETVAL trace.retval =fgraph_ret_regs_return_value (ret_regs);#endif
kernel/trace/trace.h +3 -1
@@ -911,7 +911,9 @@ extern int __trace_graph_retaddr_entry(struct trace_array *tr, unsigned long retaddr);extern void __trace_graph_return (struct trace_array *tr,struct ftrace_graph_ret *trace, -unsigned int trace_ctx); +unsigned int trace_ctx, +u64 calltime,u64 rettime); +extern void init_array_fgraph_ops (struct trace_array *tr,struct ftrace_ops *ops);extern int allocate_fgraph_ops (struct trace_array *tr,struct ftrace_ops *ops);extern void free_fgraph_ops (struct trace_array *tr);
kernel/trace/trace_entries.h +4 -4
@@ -124,8 +124,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, retval ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d retval: %lx",
@@ -146,8 +146,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, func ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d",
kernel/trace/trace_functions_graph.c +19 -14
@@ -270,12 +270,10 @@ __trace_graph_function(struct trace_array *tr,struct ftrace_graph_ret ret = { .func = ip, .depth =0 , - .calltime = time, - .rettime = time, };__trace_graph_entry (tr, &ent, trace_ctx); -__trace_graph_return (tr, &ret, trace_ctx); +__trace_graph_return (tr, &ret, trace_ctx, time, time); }void
@@ -287,8 +285,9 @@ trace_graph_function(struct trace_array *tr, }void __trace_graph_return (struct trace_array *tr, -struct ftrace_graph_ret *trace, -unsigned int trace_ctx) +struct ftrace_graph_ret *trace, +unsigned int trace_ctx, +u64 calltime,u64 rettime) {struct ring_buffer_event *event;struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -300,6 +299,8 @@ void __trace_graph_return(struct trace_array *tr,return ; entry =ring_buffer_event_data (event); entry->ret = *trace; + entry->calltime = calltime; + entry->rettime = rettime;trace_buffer_unlock_commit_nostack (buffer, event); }
@@ -322,10 +323,13 @@ void trace_graph_return(struct ftrace_graph_ret *trace,struct fgraph_times *ftimes;unsigned long flags;unsigned int trace_ctx; +u64 calltime, rettime;long disabled;int size;int cpu; + rettime =trace_clock_local (); +ftrace_graph_addr_finish (gops, trace);if (*task_var &TRACE_GRAPH_NOTRACE ) {
@@ -339,7 +343,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace,handle_nosleeptime (trace, ftimes, size); - trace->calltime = ftimes->calltime; + calltime = ftimes->calltime;local_irq_save (flags); cpu =raw_smp_processor_id ();
@@ -347,7 +351,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace, disabled =atomic_inc_return (&data->disabled);if (likely (disabled ==1 )) { trace_ctx =tracing_gen_ctx_flags (flags); -__trace_graph_return (tr, trace, trace_ctx); +__trace_graph_return (tr, trace, trace_ctx, calltime, rettime); }atomic_dec (&data->disabled);local_irq_restore (flags);
@@ -372,10 +376,8 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,handle_nosleeptime (trace, ftimes, size); - trace->calltime = ftimes->calltime; -if (tracing_thresh && - (trace->rettime - ftimes->calltime < tracing_thresh)) + (trace_clock_local () - ftimes->calltime < tracing_thresh))return ;else trace_graph_return (trace, gops);
@@ -861,7 +863,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, graph_ret = &ret_entry->ret; call = &entry->graph_ent; - duration = graph_ret->rettime - graph_ret->calltime; + duration = ret_entry->rettime - ret_entry->calltime; func = call->func + iter->tr->text_delta;
@@ -1142,11 +1144,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, }static enum print_line_t -print_graph_return (struct ftrace_graph_ret *trace,struct trace_seq *s, +print_graph_return (struct ftrace_graph_ret_entry *retentry,struct trace_seq *s,struct trace_entry *ent,struct trace_iterator *iter,u32 flags) { -unsigned long long duration = trace->rettime - trace->calltime; +struct ftrace_graph_ret *trace = &retentry->ret; +u64 calltime = retentry->calltime; +u64 rettime = retentry->rettime; +unsigned long long duration = rettime - calltime;struct fgraph_data *data = iter->private;struct trace_array *tr = iter->tr;unsigned long func;
@@ -1347,7 +1352,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)case TRACE_GRAPH_RET : {struct ftrace_graph_ret_entry *field;trace_assign_type (field, entry); -return print_graph_return (&field->ret, s, entry, iter, flags); +return print_graph_return (field, s, entry, iter, flags); }case TRACE_STACK :case TRACE_FN :
kernel/trace/trace_irqsoff.c +3 -2
@@ -221,6 +221,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,unsigned long flags;unsigned int trace_ctx;u64 *calltime; +u64 rettime;int size;ftrace_graph_addr_finish (gops, trace);
@@ -228,13 +229,13 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,if (!func_prolog_dec (tr, &data, &flags))return ; + rettime =trace_clock_local (); calltime =fgraph_retrieve_data (gops->idx, &size);if (!calltime)return ; - trace->calltime = *calltime; trace_ctx =tracing_gen_ctx_flags (flags); -__trace_graph_return (tr, trace, trace_ctx); +__trace_graph_return (tr, trace, trace_ctx, *calltime, rettime);atomic_dec (&data->disabled); }
kernel/trace/trace_sched_wakeup.c +4 -2
@@ -156,6 +156,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,struct trace_array_cpu *data;unsigned int trace_ctx;u64 *calltime; +u64 rettime;int size;ftrace_graph_addr_finish (gops, trace);
@@ -163,12 +164,13 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,if (!func_prolog_preempt_disable (tr, &data, &trace_ctx))return ; + rettime =trace_clock_local (); + calltime =fgraph_retrieve_data (gops->idx, &size);if (!calltime)return ; - trace->calltime = *calltime; -__trace_graph_return (tr, trace, trace_ctx); +__trace_graph_return (tr, trace, trace_ctx, *calltime, rettime);atomic_dec (&data->disabled);preempt_enable_notrace ();
Signature · 1 line
2.45.2
Steven Rostedt
maintainerPATCH 2/2 tracing: gfp: Remove duplication of recording GFP flags
In reply to Steven RostedtFrom: Steven Rostedt <[email protected]>
The gfp_flags when recorded in the trace require being converted from their numbers to values. Various macros are used to help facilitate this, but there's two sets of macros that need to keep track of the same GFP flags to stay in sync.
The TRACE_GFP_FLAGS macro holds the enum ___GFP_*_BIT defined bits, and creates the TRACE_DEFINE_ENUM() wrapper around them.
The __def_gfpflag_names() macro creates the mapping of various flags or multiple flags to give them human readable names via the __print_flags() tracing helper macro.
As the TRACE_GFP_FLAGS is a subset of the __def_gfpflags_names(), it can be used to cover the individual bit names, by redefining the internal macro TRACE_GFP_EM():
#undef TRACE_GFP_EM #define TRACE_GFP_EM(a) gfpflag_string(__GFP_##a),
This will remove the bits that are duplicate between the two macros. If a new bit is created, only the TRACE_GFP_FLAGS needs to be updated and that will also update the __def_gfpflags_names() macro.
--- include/trace/events/mmflags.h | 41 +++++++++------------------------- 1 file changed, 10 insertions(+), 31 deletions(-)
include/trace/events/mmflags.h +10 -31
@@ -78,6 +78,13 @@ TRACE_DEFINE_ENUM(___GFP_LAST_BIT);#define gfpflag_string (flag) {(__force unsigned long)flag, #flag} +/* +* For the values that match the bits, use the TRACE_GFP_FLAGS +* which will allow any updates to be included automatically. +*/ +#undef TRACE_GFP_EM +#define TRACE_GFP_EM (a) gfpflag_string(__GFP_##a), +#define __def_gfpflag_names \ gfpflag_string(GFP_TRANSHUGE), \ gfpflag_string(GFP_TRANSHUGE_LIGHT), \
@@ -91,41 +98,13 @@ TRACE_DEFINE_ENUM(___GFP_LAST_BIT);gfpflag_string (GFP_NOIO ), \gfpflag_string (GFP_NOWAIT ), \gfpflag_string (GFP_DMA ), \ -gfpflag_string (__GFP_HIGHMEM ), \gfpflag_string (GFP_DMA32 ), \ -gfpflag_string (__GFP_HIGH ), \ -gfpflag_string (__GFP_IO ), \ -gfpflag_string (__GFP_FS ), \ -gfpflag_string (__GFP_NOWARN ), \ -gfpflag_string (__GFP_RETRY_MAYFAIL ), \ -gfpflag_string (__GFP_NOFAIL ), \ -gfpflag_string (__GFP_NORETRY ), \ -gfpflag_string (__GFP_COMP ), \ -gfpflag_string (__GFP_ZERO ), \ -gfpflag_string (__GFP_NOMEMALLOC ), \ -gfpflag_string (__GFP_MEMALLOC ), \ -gfpflag_string (__GFP_HARDWALL ), \ -gfpflag_string (__GFP_THISNODE ), \ -gfpflag_string (__GFP_RECLAIMABLE ), \ -gfpflag_string (__GFP_MOVABLE ), \ -gfpflag_string (__GFP_ACCOUNT ), \ -gfpflag_string (__GFP_WRITE ), \gfpflag_string (__GFP_RECLAIM), \ -gfpflag_string (__GFP_DIRECT_RECLAIM ), \ -gfpflag_string (__GFP_KSWAPD_RECLAIM ), \ - gfpflag_string(__GFP_ZEROTAGS) - -#ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan , \ - gfpflag_string(__GFP_SKIP_ZERO), \ - gfpflag_string(__GFP_SKIP_KASAN) -#else -#define __def_gfpflag_names_kasan -#endif + TRACE_GFP_FLAGS \ + { 0, "none" }#define show_gfp_flags (flags) \ - (flags) ? __print_flags(flags, "|", \ - __def_gfpflag_names __def_gfpflag_names_kasan \ + (flags) ? __print_flags(flags, "|", __def_gfpflag_names \ ) : "none"#ifdef CONFIG_MMU
Signature · 1 line
2.45.2