From 877c685607925238e302cd3aa38788dca6c1b226 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 11:38:08 +0800 Subject: perf: Remove include of cgroup.h from perf_event.h Move struct perf_cgroup_info and perf_cgroup to kernel/perf/core.c, and then we can remove include of cgroup.h. Signed-off-by: Li Zefan Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tejun Heo Link: http://lkml.kernel.org/r/513568A0.6020804@huawei.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ee462c2f2..8737e1cee8b2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -21,7 +21,6 @@ */ #ifdef CONFIG_PERF_EVENTS -# include # include # include #endif @@ -299,22 +298,7 @@ struct swevent_hlist { #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 -#ifdef CONFIG_CGROUP_PERF -/* - * perf_cgroup_info keeps track of time_enabled for a cgroup. - * This is a per-cpu dynamically allocated data structure. - */ -struct perf_cgroup_info { - u64 time; - u64 timestamp; -}; - -struct perf_cgroup { - struct cgroup_subsys_state css; - struct perf_cgroup_info *info; /* timing info, one per cpu */ -}; -#endif - +struct perf_cgroup; struct ring_buffer; /** -- cgit v1.2.3 From 3a54aaa0a3ddb2cf2ec1b94a94024e9a8a8af962 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:26 +0100 Subject: perf/x86: Improve sysfs event mapping with event string This patch extends Jiri's changes to make generic events mapping visible via sysfs. The patch extends the mechanism to non-generic events by allowing the mappings to be hardcoded in strings. This mechanism will be used by the PEBS-LL patch later on. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar [ fixed up conflict with 2663960 "perf: Make EVENT_ATTR global" ] Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8737e1cee8b2..1c592114c437 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -809,6 +809,7 @@ do { \ struct perf_pmu_events_attr { struct device_attribute attr; u64 id; + const char *event_str; }; #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ -- cgit v1.2.3 From 9fac2cf316b070ae43d2ae2525e381ff2d1d68aa Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:27 +0100 Subject: perf/x86: Add flags to event constraints This patch adds a flags field to each event constraint. It can be used to store event specific features which can then later be used by scheduling code or low-level x86 code. The flags are propagated into event->hw.flags during the get_event_constraint() call. They are cleared during the put_event_constraint() call. This mechanism is going to be used by the PEBS-LL patches. It avoids defining yet another table to hold event specific information. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-4-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1c592114c437..cd3bb2cd9494 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -127,6 +127,7 @@ struct hw_perf_event { int event_base_rdpmc; int idx; int last_cpu; + int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; -- cgit v1.2.3 From c3feedf2aaf9ac8bad6f19f5d21e4ee0b4b87e9c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 24 Jan 2013 16:10:28 +0100 Subject: perf/core: Add weighted samples For some events it's useful to weight sample with a hardware provided number. This expresses how expensive the action the sample represent was. This allows the profiler to scale the samples to be more informative to the programmer. There is already the period which is used similarly, but it means something different, so I chose to not overload it. Instead a new sample type for WEIGHT is added. Can be used for multiple things. Initially it is used for TSX abort costs and profiling by memory latencies (so to make expensive load appear higher up in the histograms). The concept is quite generic and can be extended to many other kinds of events or architectures, as long as the hardware provides suitable auxillary values. In principle it could be also used for software tracepoints. This adds the generic glue. A new optional sample format for a 64-bit weight value. Signed-off-by: Andi Kleen Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-5-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cd3bb2cd9494..7ce0b37b155b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -573,6 +573,7 @@ struct perf_sample_data { struct perf_branch_stack *br_stack; struct perf_regs_user regs_user; u64 stack_user_size; + u64 weight; }; static inline void perf_sample_data_init(struct perf_sample_data *data, @@ -586,6 +587,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE; data->regs_user.regs = NULL; data->stack_user_size = 0; + data->weight = 0; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From d6be9ad6c960f43800a6f118932bc8a5a4eadcd1 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:31 +0100 Subject: perf: Add generic memory sampling interface This patch adds PERF_SAMPLE_DATA_SRC. PERF_SAMPLE_DATA_SRC collects the data source, i.e., where did the data associated with the sampled instruction come from. Information is stored in a perf_mem_data_src structure. It contains opcode, mem level, tlb, snoop, lock information, subject to availability in hardware. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-8-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7ce0b37b155b..42a6daaf4e0a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -568,6 +568,7 @@ struct perf_sample_data { 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; @@ -588,6 +589,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->regs_user.regs = NULL; data->stack_user_size = 0; data->weight = 0; + data->data_src.val = 0; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From 0908ad6e56b5a6e86745680bc324bdbfac64d0b6 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Fri, 22 Mar 2013 20:46:27 +0530 Subject: uprobes: Add trap variant helper Some architectures like powerpc have multiple variants of the trap instruction. Introduce an additional helper is_trap_insn() for run-time handling of non-uprobe traps on such architectures. While there, change is_swbp_at_addr() to is_trap_at_addr() for reading clarity. With this change, the uprobe registration path will supercede any trap instruction inserted at the requested location, while taking care of delivering the SIGTRAP for cases where the trap notification came in for an address without a uprobe. See [1] for a more detailed explanation. [1] https://lists.ozlabs.org/pipermail/linuxppc-dev/2013-March/104771.html This change was suggested by Oleg Nesterov. Signed-off-by: Ananth N Mavinakayanahalli Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 02b83db8e2c5..19612881399a 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -100,6 +100,7 @@ struct uprobes_state { extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool __weak is_swbp_insn(uprobe_opcode_t *insn); +extern bool __weak is_trap_insn(uprobe_opcode_t *insn); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -- cgit v1.2.3 From 324670b620ab1ed00ba160e435686bd2ae4a59ce Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 4 Apr 2013 19:40:50 +0900 Subject: kprobes: Move __kprobes definition into compiler.h Currently, __kprobes is defined in linux/kprobes.h which is too big to be included in small or basic headers that want to make use of this simple attribute. So move __kprobes definition into linux/compiler.h in which other compiler attributes are defined. Signed-off-by: Masami Hiramatsu Cc: Timo Juhani Lindfors Cc: Ananth N Mavinakayanahalli Cc: Pavel Emelyanov Cc: Jiri Kosina Cc: Nadia Yvette Chambers Cc: yrl.pp-manager.tt@hitachi.com Cc: David S. Miller Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20130404104049.21071.20908.stgit@mhiramat-M0-7522 [ Improved the attribute explanation a bit. ] Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 6 ++++++ include/linux/kprobes.h | 6 +----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 10b8f23fab0f..92669cd182a6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -351,4 +351,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) +/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ +#ifdef CONFIG_KPROBES +# define __kprobes __attribute__((__section__(".kprobes.text"))) +#else +# define __kprobes +#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 4b6ef4d33cc2..ca1d27a0d6a6 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -29,6 +29,7 @@ * and Prasanna S Panchamukhi * added function-return probes. */ +#include /* for __kprobes */ #include #include #include @@ -49,16 +50,11 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 -/* Attach to insert probes on any functions which should be ignored*/ -#define __kprobes __attribute__((__section__(".kprobes.text"))) - #else /* CONFIG_KPROBES */ typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; }; -#define __kprobes - #endif /* CONFIG_KPROBES */ struct kprobe; -- cgit v1.2.3 From ea024870cf10687b3fded66a9deb6253888f30b7 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:31 +0200 Subject: uretprobes: Introduce uprobe_consumer->ret_handler() Enclose return probes implementation, introduce ->ret_handler() and update existing code to rely on ->handler() *and* ->ret_handler() for uprobe and uretprobe respectively. Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 19612881399a..5c8d3290df41 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -46,6 +46,9 @@ enum uprobe_filter_ctx { struct uprobe_consumer { int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); + int (*ret_handler)(struct uprobe_consumer *self, + unsigned long func, + struct pt_regs *regs); bool (*filter)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); -- cgit v1.2.3 From 0dfd0eb8e4d72ded8b21f4fee74ba5547408cbe9 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:35 +0200 Subject: uretprobes: Return probe entry, prepare_uretprobe() When a uprobe with return probe consumer is hit, prepare_uretprobe() function is invoked. It creates return_instance, hijacks return address and replaces it with the trampoline. * Return instances are kept as stack per uprobed task. * Return instance is chained, when the original return address is trampoline's page vaddr (e.g. recursive call of the probed function). Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 5c8d3290df41..b0507f24eeb0 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -71,6 +71,7 @@ struct uprobe_task { enum uprobe_task_state state; struct arch_uprobe_task autask; + struct return_instance *return_instances; struct uprobe *active_uprobe; unsigned long xol_vaddr; -- cgit v1.2.3 From ded49c55309a37129dc30a5f0e85b8a64e5c1716 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:37 +0200 Subject: uretprobes: Limit the depth of return probe nestedness Unlike the kretprobes we can't trust userspace, thus must have protection from user space attacks. User-space have "unlimited" stack, and this patch limits the return probes nestedness as a simple remedy for it. Note that this implementation leaks return_instance on siglongjmp until exit()/exec(). The intention is to have KISS and bare minimum solution for the initial implementation in order to not complicate the uretprobes code. In the future we may come up with more sophisticated solution that remove this depth limitation. It is not easy task and lays beyond this patchset. Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b0507f24eeb0..06f28beed7c2 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -38,6 +38,8 @@ struct inode; #define UPROBE_HANDLER_REMOVE 1 #define UPROBE_HANDLER_MASK 1 +#define MAX_URETPROBE_DEPTH 64 + enum uprobe_filter_ctx { UPROBE_FILTER_REGISTER, UPROBE_FILTER_UNREGISTER, @@ -72,6 +74,7 @@ struct uprobe_task { struct arch_uprobe_task autask; struct return_instance *return_instances; + unsigned int depth; struct uprobe *active_uprobe; unsigned long xol_vaddr; -- cgit v1.2.3