From 60e2364e60e86e81bc6377f49779779e6120977f Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 24 Sep 2014 13:48:37 +0200 Subject: perf: Add ability to sample machine state on interrupt Enable capture of interrupted machine state for each sample. Registers to sample are passed per event in the sample_regs_intr bitmask. To sample interrupt machine state, the PERF_SAMPLE_INTR_REGS must be passed in sample_type. The list of available registers is arch dependent and provided by asm/perf_regs.h Registers are laid out as u64 in the order of the bit order of sample_intr_regs. This patch also adds a new ABI version PERF_ATTR_SIZE_VER4 because we extend the perf_event_attr struct with a new u64 field. Reviewed-by: Jiri Olsa Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: cebbert.lkml@gmail.com Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1411559322-16548-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 893a0d07986f..68d46d536e24 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -79,7 +79,7 @@ struct perf_branch_stack { struct perf_branch_entry entries[0]; }; -struct perf_regs_user { +struct perf_regs { __u64 abi; struct pt_regs *regs; }; @@ -600,7 +600,8 @@ struct perf_sample_data { struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; - struct perf_regs_user regs_user; + struct perf_regs regs_user; + struct perf_regs regs_intr; u64 stack_user_size; u64 weight; /* @@ -630,6 +631,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; + data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE; + data->regs_intr.regs = NULL; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From 2565711fb7d7c28e0cd93c8971b520d1b10b857c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Sep 2014 13:48:42 +0200 Subject: perf: Improve the perf_sample_data struct layout This patch reorders fields in the perf_sample_data struct in order to minimize the number of cachelines touched in perf_sample_data_init(). It also removes some intializations which are redundant with the code in kernel/events/core.c Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/1411559322-16548-7-git-send-email-eranian@google.com Cc: cebbert.lkml@gmail.com Cc: Arnaldo Carvalho de Melo Cc: jolsa@redhat.com Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux/perf_event.h') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 68d46d536e24..486e84ccb1f9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -580,35 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event, struct perf_sample_data { - u64 type; + /* + * Fields set by perf_sample_data_init(), group so as to + * minimize the cachelines touched. + */ + u64 addr; + struct perf_raw_record *raw; + struct perf_branch_stack *br_stack; + u64 period; + u64 weight; + u64 txn; + union perf_mem_data_src data_src; + /* + * The other fields, optionally {set,used} by + * perf_{prepare,output}_sample(). + */ + u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; - u64 addr; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; - u64 period; - union perf_mem_data_src data_src; struct perf_callchain_entry *callchain; - struct perf_raw_record *raw; - struct perf_branch_stack *br_stack; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; - u64 weight; - /* - * Transaction flags for abort events: - */ - u64 txn; -}; +} ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ @@ -625,14 +630,9 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->raw = NULL; data->br_stack = NULL; data->period = period; - data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE; - data->regs_user.regs = NULL; - data->stack_user_size = 0; data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; - data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE; - data->regs_intr.regs = NULL; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3