diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-01 10:28:49 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-01 10:28:49 -0700 |
| commit | 7e92daaefa68e5ef1e1732e45231e73adbb724e7 (patch) | |
| tree | 8e7f8ac9d82654df4c65939c6682f95510e22977 | |
| parent | 7a68294278ae714ce2632a54f0f46916dca64f56 (diff) | |
| parent | 1d787d37c8ff6612b8151c6dff15bfa7347bcbdf (diff) | |
| download | linux-7e92daaefa68e5ef1e1732e45231e73adbb724e7.tar.bz2 | |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf update from Ingo Molnar:
"Lots of changes in this cycle as well, with hundreds of commits from
over 30 contributors. Most of the activity was on the tooling side.
Higher level changes:
- New 'perf kvm' analysis tool, from Xiao Guangrong.
- New 'perf trace' system-wide tracing tool
- uprobes fixes + cleanups from Oleg Nesterov.
- Lots of patches to make perf build on Android out of box, from
Irina Tirdea
- Extend ftrace function tracing utility to be more dynamic for its
users. It allows for data passing to the callback functions, as
well as reading regs as if a breakpoint were to trigger at function
entry.
The main goal of this patch series was to allow kprobes to use
ftrace as an optimized probe point when a probe is placed on an
ftrace nop. With lots of help from Masami Hiramatsu, and going
through lots of iterations, we finally came up with a good
solution.
- Add cpumask for uncore pmu, use it in 'stat', from Yan, Zheng.
- Various tracing updates from Steve Rostedt
- Clean up and improve 'perf sched' performance by elliminating lots
of needless calls to libtraceevent.
- Event group parsing support, from Jiri Olsa
- UI/gtk refactorings and improvements from Namhyung Kim
- Add support for non-tracepoint events in perf script python, from
Feng Tang
- Add --symbols to 'script', similar to the one in 'report', from
Feng Tang.
Infrastructure enhancements and fixes:
- Convert the trace builtins to use the growing evsel/evlist
tracepoint infrastructure, removing several open coded constructs
like switch like series of strcmp to dispatch events, etc.
Basically what had already been showcased in 'perf sched'.
- Add evsel constructor for tracepoints, that uses libtraceevent just
to parse the /format events file, use it in a new 'perf test' to
make sure the libtraceevent format parsing regressions can be more
readily caught.
- Some strange errors were happening in some builds, but not on the
next, reported by several people, problem was some parser related
files, generated during the build, didn't had proper make deps, fix
from Eric Sandeen.
- Introduce struct and cache information about the environment where
a perf.data file was captured, from Namhyung Kim.
- Fix handling of unresolved samples when --symbols is used in
'report', from Feng Tang.
- Add union member access support to 'probe', from Hyeoncheol Lee.
- Fixups to die() removal, from Namhyung Kim.
- Render fixes for the TUI, from Namhyung Kim.
- Don't enable annotation in non symbolic view, from Namhyung Kim.
- Fix pipe mode in 'report', from Namhyung Kim.
- Move related stats code from stat to util/, will be used by the
'stat' kvm tool, from Xiao Guangrong.
- Remove die()/exit() calls from several tools.
- Resolve vdso callchains, from Jiri Olsa
- Don't pass const char pointers to basename, so that we can
unconditionally use libgen.h and thus avoid ifdef BIONIC lines,
from David Ahern
- Refactor hist formatting so that it can be reused with the GTK
browser, From Namhyung Kim
- Fix build for another rbtree.c change, from Adrian Hunter.
- Make 'perf diff' command work with evsel hists, from Jiri Olsa.
- Use the only field_sep var that is set up: symbol_conf.field_sep,
fix from Jiri Olsa.
- .gitignore compiled python binaries, from Namhyung Kim.
- Get rid of die() in more libtraceevent places, from Namhyung Kim.
- Rename libtraceevent 'private' struct member to 'priv' so that it
works in C++, from Steven Rostedt
- Remove lots of exit()/die() calls from tools so that the main perf
exit routine can take place, from David Ahern
- Fix x86 build on x86-64, from David Ahern.
- {int,str,rb}list fixes from Suzuki K Poulose
- perf.data header fixes from Namhyung Kim
- Allow user to indicate objdump path, needed in cross environments,
from Maciek Borzecki
- Fix hardware cache event name generation, fix from Jiri Olsa
- Add round trip test for sw, hw and cache event names, catching the
problem Jiri fixed, after Jiri's patch, the test passes
successfully.
- Clean target should do clean for lib/traceevent too, fix from David
Ahern
- Check the right variable for allocation failure, fix from Namhyung
Kim
- Set up evsel->tp_format regardless of evsel->name being set
already, fix from Namhyung Kim
- Oprofile fixes from Robert Richter.
- Remove perf_event_attr needless version inflation, from Jiri Olsa
- Introduce libtraceevent strerror like error reporting facility,
from Namhyung Kim
- Add pmu mappings to perf.data header and use event names from cmd
line, from Robert Richter
- Fix include order for bison/flex-generated C files, from Ben
Hutchings
- Build fixes and documentation corrections from David Ahern
- Assorted cleanups from Robert Richter
- Let O= makes handle relative paths, from Steven Rostedt
- perf script python fixes, from Feng Tang.
- Initial bash completion support, from Frederic Weisbecker
- Allow building without libelf, from Namhyung Kim.
- Support DWARF CFI based unwind to have callchains when %bp based
unwinding is not possible, from Jiri Olsa.
- Symbol resolution fixes, while fixing support PPC64 files with an
.opt ELF section was the end goal, several fixes for code that
handles all architectures and cleanups are included, from Cody
Schafer.
- Assorted fixes for Documentation and build in 32 bit, from Robert
Richter
- Cache the libtraceevent event_format associated to each evsel
early, so that we avoid relookups, i.e. calling pevent_find_event
repeatedly when processing tracepoint events.
[ This is to reduce the surface contact with libtraceevents and
make clear what is that the perf tools needs from that lib: so
far parsing the common and per event fields. ]
- Don't stop the build if the audit libraries are not installed, fix
from Namhyung Kim.
- Fix bfd.h/libbfd detection with recent binutils, from Markus
Trippelsdorf.
- Improve warning message when libunwind devel packages not present,
from Jiri Olsa"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (282 commits)
perf trace: Add aliases for some syscalls
perf probe: Print an enum type variable in "enum variable-name" format when showing accessible variables
perf tools: Check libaudit availability for perf-trace builtin
perf hists: Add missing period_* fields when collapsing a hist entry
perf trace: New tool
perf evsel: Export the event_format constructor
perf evsel: Introduce rawptr() method
perf tools: Use perf_evsel__newtp in the event parser
perf evsel: The tracepoint constructor should store sys:name
perf evlist: Introduce set_filter() method
perf evlist: Renane set_filters method to apply_filters
perf test: Add test to check we correctly parse and match syscall open parms
perf evsel: Handle endianity in intval method
perf evsel: Know if byte swap is needed
perf tools: Allow handling a NULL cpu_map as meaning "all cpus"
perf evsel: Improve tracepoint constructor setup
tools lib traceevent: Fix error path on pevent_parse_event
perf test: Fix build failure
trace: Move trace event enable from fs_initcall to core_initcall
tracing: Add an option for disabling markers
...
208 files changed, 13242 insertions, 5240 deletions
@@ -609,7 +609,11 @@ KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) endif ifdef CONFIG_FUNCTION_TRACER -KBUILD_CFLAGS += -pg +ifdef CONFIG_HAVE_FENTRY +CC_USING_FENTRY := $(call cc-option, -mfentry -DCC_USING_FENTRY) +endif +KBUILD_CFLAGS += -pg $(CC_USING_FENTRY) +KBUILD_AFLAGS += $(CC_USING_FENTRY) ifdef CONFIG_DYNAMIC_FTRACE ifdef CONFIG_HAVE_C_RECORDMCOUNT BUILD_C_RECORDMCOUNT := y diff --git a/arch/Kconfig b/arch/Kconfig index 1401a7587973..1a7b468abf4a 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -222,6 +222,19 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_PERF_REGS + bool + help + Support selective register dumps for perf events. This includes + bit-mapping of each registers and a unique architecture id. + +config HAVE_PERF_USER_STACK_DUMP + bool + help + Support user stack dumps for perf event samples. This needs + access to the user stack pointer which is not unified across + architectures. + config HAVE_ARCH_JUMP_LABEL bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 20c49b8450b8..8ff1f56a0188 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -36,6 +36,7 @@ config X86 select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FENTRY if X86_64 select HAVE_C_RECORDMCOUNT select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -60,6 +61,8 @@ config X86 select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select ANON_INODES select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386 select HAVE_CMPXCHG_LOCAL if !M386 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b0767bc08740..9a25b522d377 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -3,38 +3,54 @@ #ifdef __ASSEMBLY__ - .macro MCOUNT_SAVE_FRAME - /* taken from glibc */ - subq $0x38, %rsp - movq %rax, (%rsp) - movq %rcx, 8(%rsp) - movq %rdx, 16(%rsp) - movq %rsi, 24(%rsp) - movq %rdi, 32(%rsp) - movq %r8, 40(%rsp) - movq %r9, 48(%rsp) + /* skip is set if the stack was already partially adjusted */ + .macro MCOUNT_SAVE_FRAME skip=0 + /* + * We add enough stack to save all regs. + */ + subq $(SS+8-\skip), %rsp + movq %rax, RAX(%rsp) + movq %rcx, RCX(%rsp) + movq %rdx, RDX(%rsp) + movq %rsi, RSI(%rsp) + movq %rdi, RDI(%rsp) + movq %r8, R8(%rsp) + movq %r9, R9(%rsp) + /* Move RIP to its proper location */ + movq SS+8(%rsp), %rdx + movq %rdx, RIP(%rsp) .endm - .macro MCOUNT_RESTORE_FRAME - movq 48(%rsp), %r9 - movq 40(%rsp), %r8 - movq 32(%rsp), %rdi - movq 24(%rsp), %rsi - movq 16(%rsp), %rdx - movq 8(%rsp), %rcx - movq (%rsp), %rax - addq $0x38, %rsp + .macro MCOUNT_RESTORE_FRAME skip=0 + movq R9(%rsp), %r9 + movq R8(%rsp), %r8 + movq RDI(%rsp), %rdi + movq RSI(%rsp), %rsi + movq RDX(%rsp), %rdx + movq RCX(%rsp), %rcx + movq RAX(%rsp), %rax + addq $(SS+8-\skip), %rsp .endm #endif #ifdef CONFIG_FUNCTION_TRACER -#define MCOUNT_ADDR ((long)(mcount)) +#ifdef CC_USING_FENTRY +# define MCOUNT_ADDR ((long)(__fentry__)) +#else +# define MCOUNT_ADDR ((long)(mcount)) +#endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ +#ifdef CONFIG_DYNAMIC_FTRACE +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#define ARCH_SUPPORTS_FTRACE_SAVE_REGS +#endif + #ifndef __ASSEMBLY__ extern void mcount(void); extern atomic_t modifying_ftrace_code; +extern void __fentry__(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 547882539157..d3ddd17405d0 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -27,6 +27,7 @@ #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT +#define ARCH_SUPPORTS_KPROBES_ON_FTRACE struct pt_regs; struct kprobe; diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 246617efd67f..41e08cb6a092 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -9,6 +9,22 @@ #include <linux/types.h> #include <linux/ioctl.h> +#define DE_VECTOR 0 +#define DB_VECTOR 1 +#define BP_VECTOR 3 +#define OF_VECTOR 4 +#define BR_VECTOR 5 +#define UD_VECTOR 6 +#define NM_VECTOR 7 +#define DF_VECTOR 8 +#define TS_VECTOR 10 +#define NP_VECTOR 11 +#define SS_VECTOR 12 +#define GP_VECTOR 13 +#define PF_VECTOR 14 +#define MF_VECTOR 16 +#define MC_VECTOR 18 + /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT #define __KVM_HAVE_IOAPIC diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 09155d64cf7e..1eaa6b056670 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -75,22 +75,6 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) -#define DE_VECTOR 0 -#define DB_VECTOR 1 -#define BP_VECTOR 3 -#define OF_VECTOR 4 -#define BR_VECTOR 5 -#define UD_VECTOR 6 -#define NM_VECTOR 7 -#define DF_VECTOR 8 -#define TS_VECTOR 10 -#define NP_VECTOR 11 -#define SS_VECTOR 12 -#define GP_VECTOR 13 -#define PF_VECTOR 14 -#define MF_VECTOR 16 -#define MC_VECTOR 18 - #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index cb4e43bce98a..4fabcdf1cfa7 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -262,4 +262,6 @@ static inline void perf_check_microcode(void) { } static inline void amd_pmu_disable_virt(void) { } #endif +#define arch_perf_out_copy_user copy_from_user_nmi + #endif /* _ASM_X86_PERF_EVENT_H */ diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h new file mode 100644 index 000000000000..3f2207bfd17b --- /dev/null +++ b/arch/x86/include/asm/perf_regs.h @@ -0,0 +1,33 @@ +#ifndef _ASM_X86_PERF_REGS_H +#define _ASM_X86_PERF_REGS_H + +enum perf_event_x86_regs { + PERF_REG_X86_AX, + PERF_REG_X86_BX, + PERF_REG_X86_CX, + PERF_REG_X86_DX, + PERF_REG_X86_SI, + PERF_REG_X86_DI, + PERF_REG_X86_BP, + PERF_REG_X86_SP, + PERF_REG_X86_IP, + PERF_REG_X86_FLAGS, + PERF_REG_X86_CS, + PERF_REG_X86_SS, + PERF_REG_X86_DS, + PERF_REG_X86_ES, + PERF_REG_X86_FS, + PERF_REG_X86_GS, + PERF_REG_X86_R8, + PERF_REG_X86_R9, + PERF_REG_X86_R10, + PERF_REG_X86_R11, + PERF_REG_X86_R12, + PERF_REG_X86_R13, + PERF_REG_X86_R14, + PERF_REG_X86_R15, + + PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, + PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, +}; +#endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d048cad9bcad..433d2e5c98a7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -759,6 +759,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } +extern void set_task_blockstep(struct task_struct *task, bool on); + /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f2b83bc7d784..cdf5674dd23a 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -1,6 +1,135 @@ #ifndef __SVM_H #define __SVM_H +#define SVM_EXIT_READ_CR0 0x000 +#define SVM_EXIT_READ_CR3 0x003 +#define SVM_EXIT_READ_CR4 0x004 +#define SVM_EXIT_READ_CR8 0x008 +#define SVM_EXIT_WRITE_CR0 0x010 +#define SVM_EXIT_WRITE_CR3 0x013 +#define SVM_EXIT_WRITE_CR4 0x014 +#define SVM_EXIT_WRITE_CR8 0x018 +#define SVM_EXIT_READ_DR0 0x020 +#define SVM_EXIT_READ_DR1 0x021 +#define SVM_EXIT_READ_DR2 0x022 +#define SVM_EXIT_READ_DR3 0x023 +#define SVM_EXIT_READ_DR4 0x024 +#define SVM_EXIT_READ_DR5 0x025 +#define SVM_EXIT_READ_DR6 0x026 +#define SVM_EXIT_READ_DR7 0x027 +#define SVM_EXIT_WRITE_DR0 0x030 +#define SVM_EXIT_WRITE_DR1 0x031 +#define SVM_EXIT_WRITE_DR2 0x032 +#define SVM_EXIT_WRITE_DR3 0x033 +#define SVM_EXIT_WRITE_DR4 0x034 +#define SVM_EXIT_WRITE_DR5 0x035 +#define SVM_EXIT_WRITE_DR6 0x036 +#define SVM_EXIT_WRITE_DR7 0x037 +#define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_INTR 0x060 +#define SVM_EXIT_NMI 0x061 +#define SVM_EXIT_SMI 0x062 +#define SVM_EXIT_INIT 0x063 +#define SVM_EXIT_VINTR 0x064 +#define SVM_EXIT_CR0_SEL_WRITE 0x065 +#define SVM_EXIT_IDTR_READ 0x066 +#define SVM_EXIT_GDTR_READ 0x067 +#define SVM_EXIT_LDTR_READ 0x068 +#define SVM_EXIT_TR_READ 0x069 +#define SVM_EXIT_IDTR_WRITE 0x06a +#define SVM_EXIT_GDTR_WRITE 0x06b +#define SVM_EXIT_LDTR_WRITE 0x06c +#define SVM_EXIT_TR_WRITE 0x06d +#define SVM_EXIT_RDTSC 0x06e +#define SVM_EXIT_RDPMC 0x06f +#define SVM_EXIT_PUSHF 0x070 +#define SVM_EXIT_POPF 0x071 +#define SVM_EXIT_CPUID 0x072 +#define SVM_EXIT_RSM 0x073 +#define SVM_EXIT_IRET 0x074 +#define SVM_EXIT_SWINT 0x075 +#define SVM_EXIT_INVD 0x076 +#define SVM_EXIT_PAUSE 0x077 +#define SVM_EXIT_HLT 0x078 +#define SVM_EXIT_INVLPG 0x079 +#define SVM_EXIT_INVLPGA 0x07a +#define SVM_EXIT_IOIO 0x07b +#define SVM_EXIT_MSR 0x07c +#define SVM_EXIT_TASK_SWITCH 0x07d +#define SVM_EXIT_FERR_FREEZE 0x07e +#define SVM_EXIT_SHUTDOWN 0x07f +#define SVM_EXIT_VMRUN 0x080 +#define SVM_EXIT_VMMCALL 0x081 +#define SVM_EXIT_VMLOAD 0x082 +#define SVM_EXIT_VMSAVE 0x083 +#define SVM_EXIT_STGI 0x084 +#define SVM_EXIT_CLGI 0x085 +#define SVM_EXIT_SKINIT 0x086 +#define SVM_EXIT_RDTSCP 0x087 +#define SVM_EXIT_ICEBP 0x088 +#define SVM_EXIT_WBINVD 0x089 +#define SVM_EXIT_MONITOR 0x08a +#define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_MWAIT_COND 0x08c +#define SVM_EXIT_XSETBV 0x08d +#define SVM_EXIT_NPF 0x400 + +#define SVM_EXIT_ERR -1 + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + +#ifdef __KERNEL__ + enum { INTERCEPT_INTR, INTERCEPT_NMI, @@ -264,81 +393,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_EXITINFO_REG_MASK 0x0F -#define SVM_EXIT_READ_CR0 0x000 -#define SVM_EXIT_READ_CR3 0x003 -#define SVM_EXIT_READ_CR4 0x004 -#define SVM_EXIT_READ_CR8 0x008 -#define SVM_EXIT_WRITE_CR0 0x010 -#define SVM_EXIT_WRITE_CR3 0x013 -#define SVM_EXIT_WRITE_CR4 0x014 -#define SVM_EXIT_WRITE_CR8 0x018 -#define SVM_EXIT_READ_DR0 0x020 -#define SVM_EXIT_READ_DR1 0x021 -#define SVM_EXIT_READ_DR2 0x022 -#define SVM_EXIT_READ_DR3 0x023 -#define SVM_EXIT_READ_DR4 0x024 -#define SVM_EXIT_READ_DR5 0x025 -#define SVM_EXIT_READ_DR6 0x026 -#define SVM_EXIT_READ_DR7 0x027 -#define SVM_EXIT_WRITE_DR0 0x030 -#define SVM_EXIT_WRITE_DR1 0x031 -#define SVM_EXIT_WRITE_DR2 0x032 -#define SVM_EXIT_WRITE_DR3 0x033 -#define SVM_EXIT_WRITE_DR4 0x034 -#define SVM_EXIT_WRITE_DR5 0x035 -#define SVM_EXIT_WRITE_DR6 0x036 -#define SVM_EXIT_WRITE_DR7 0x037 -#define SVM_EXIT_EXCP_BASE 0x040 -#define SVM_EXIT_INTR 0x060 -#define SVM_EXIT_NMI 0x061 -#define SVM_EXIT_SMI 0x062 -#define SVM_EXIT_INIT 0x063 -#define SVM_EXIT_VINTR 0x064 -#define SVM_EXIT_CR0_SEL_WRITE 0x065 -#define SVM_EXIT_IDTR_READ 0x066 -#define SVM_EXIT_GDTR_READ 0x067 -#define SVM_EXIT_LDTR_READ 0x068 -#define SVM_EXIT_TR_READ 0x069 -#define SVM_EXIT_IDTR_WRITE 0x06a -#define SVM_EXIT_GDTR_WRITE 0x06b -#define SVM_EXIT_LDTR_WRITE 0x06c -#define SVM_EXIT_TR_WRITE 0x06d -#define SVM_EXIT_RDTSC 0x06e -#define SVM_EXIT_RDPMC 0x06f -#define SVM_EXIT_PUSHF 0x070 -#define SVM_EXIT_POPF 0x071 -#define SVM_EXIT_CPUID 0x072 -#define SVM_EXIT_RSM 0x073 -#define SVM_EXIT_IRET 0x074 -#define SVM_EXIT_SWINT 0x075 -#define SVM_EXIT_INVD 0x076 -#define SVM_EXIT_PAUSE 0x077 -#define SVM_EXIT_HLT 0x078 -#define SVM_EXIT_INVLPG 0x079 -#define SVM_EXIT_INVLPGA 0x07a -#define SVM_EXIT_IOIO 0x07b -#define SVM_EXIT_MSR 0x07c -#define SVM_EXIT_TASK_SWITCH 0x07d -#define SVM_EXIT_FERR_FREEZE 0x07e -#define SVM_EXIT_SHUTDOWN 0x07f -#define SVM_EXIT_VMRUN 0x080 -#define SVM_EXIT_VMMCALL 0x081 -#define SVM_EXIT_VMLOAD 0x082 -#define SVM_EXIT_VMSAVE 0x083 -#define SVM_EXIT_STGI 0x084 -#define SVM_EXIT_CLGI 0x085 -#define SVM_EXIT_SKINIT 0x086 -#define SVM_EXIT_RDTSCP 0x087 -#define SVM_EXIT_ICEBP 0x088 -#define SVM_EXIT_WBINVD 0x089 -#define SVM_EXIT_MONITOR 0x08a -#define SVM_EXIT_MWAIT 0x08b -#define SVM_EXIT_MWAIT_COND 0x08c -#define SVM_EXIT_XSETBV 0x08d -#define SVM_EXIT_NPF 0x400 - -#define SVM_EXIT_ERR -1 - #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" @@ -350,3 +404,4 @@ struct __attribute__ ((__packed__)) vmcb { #endif +#endif diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index f3971bbcd1de..8ff8be7835ab 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -42,10 +42,11 @@ struct arch_uprobe { }; struct arch_uprobe_task { - unsigned long saved_trap_nr; #ifdef CONFIG_X86_64 unsigned long saved_scratch_register; #endif + unsigned int saved_trap_nr; + unsigned int saved_tf; }; extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 74fcb963595b..36ec21c36d68 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -25,6 +25,88 @@ * */ +#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 + +#define EXIT_REASON_EXCEPTION_NMI 0 +#define EXIT_REASON_EXTERNAL_INTERRUPT 1 +#define EXIT_REASON_TRIPLE_FAULT 2 + +#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_NMI_WINDOW 8 +#define EXIT_REASON_TASK_SWITCH 9 +#define EXIT_REASON_CPUID 10 +#define EXIT_REASON_HLT 12 +#define EXIT_REASON_INVD 13 +#define EXIT_REASON_INVLPG 14 +#define EXIT_REASON_RDPMC 15 +#define EXIT_REASON_RDTSC 16 +#define EXIT_REASON_VMCALL 18 +#define EXIT_REASON_VMCLEAR 19 +#define EXIT_REASON_VMLAUNCH 20 +#define EXIT_REASON_VMPTRLD 21 +#define EXIT_REASON_VMPTRST 22 +#define EXIT_REASON_VMREAD 23 +#define EXIT_REASON_VMRESUME 24 +#define EXIT_REASON_VMWRITE 25 +#define EXIT_REASON_VMOFF 26 +#define EXIT_REASON_VMON 27 +#define EXIT_REASON_CR_ACCESS 28 +#define EXIT_REASON_DR_ACCESS 29 +#define EXIT_REASON_IO_INSTRUCTION 30 +#define EXIT_REASON_MSR_READ 31 +#define EXIT_REASON_MSR_WRITE 32 +#define EXIT_REASON_INVALID_STATE 33 +#define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_INSTRUCTION 39 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 +#define EXIT_REASON_MCE_DURING_VMENTRY 41 +#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 +#define EXIT_REASON_APIC_ACCESS 44 +#define EXIT_REASON_EPT_VIOLATION 48 +#define EXIT_REASON_EPT_MISCONFIG 49 +#define EXIT_REASON_WBINVD 54 +#define EXIT_REASON_XSETBV 55 +#define EXIT_REASON_INVPCID 58 + +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#ifdef __KERNEL__ + #include <linux/types.h> /* @@ -241,49 +323,6 @@ enum vmcs_field { HOST_RIP = 0x00006c16, }; -#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 - -#define EXIT_REASON_EXCEPTION_NMI 0 -#define EXIT_REASON_EXTERNAL_INTERRUPT 1 -#define EXIT_REASON_TRIPLE_FAULT 2 - -#define EXIT_REASON_PENDING_INTERRUPT 7 -#define EXIT_REASON_NMI_WINDOW 8 -#define EXIT_REASON_TASK_SWITCH 9 -#define EXIT_REASON_CPUID 10 -#define EXIT_REASON_HLT 12 -#define EXIT_REASON_INVD 13 -#define EXIT_REASON_INVLPG 14 -#define EXIT_REASON_RDPMC 15 -#define EXIT_REASON_RDTSC 16 -#define EXIT_REASON_VMCALL 18 -#define EXIT_REASON_VMCLEAR 19 -#define EXIT_REASON_VMLAUNCH 20 -#define EXIT_REASON_VMPTRLD 21 -#define EXIT_REASON_VMPTRST 22 -#define EXIT_REASON_VMREAD 23 -#define EXIT_REASON_VMRESUME 24 -#define EXIT_REASON_VMWRITE 25 -#define EXIT_REASON_VMOFF 26 -#define EXIT_REASON_VMON 27 -#define EXIT_REASON_CR_ACCESS 28 -#define EXIT_REASON_DR_ACCESS 29 -#define EXIT_REASON_IO_INSTRUCTION 30 -#define EXIT_REASON_MSR_READ 31 -#define EXIT_REASON_MSR_WRITE 32 -#define EXIT_REASON_INVALID_STATE 33 -#define EXIT_REASON_MWAIT_INSTRUCTION 36 -#define EXIT_REASON_MONITOR_INSTRUCTION 39 -#define EXIT_REASON_PAUSE_INSTRUCTION 40 -#define EXIT_REASON_MCE_DURING_VMENTRY 41 -#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 -#define EXIT_REASON_APIC_ACCESS 44 -#define EXIT_REASON_EPT_VIOLATION 48 -#define EXIT_REASON_EPT_MISCONFIG 49 -#define EXIT_REASON_WBINVD 54 -#define EXIT_REASON_XSETBV 55 -#define EXIT_REASON_INVPCID 58 - /* * Interruption-information format */ @@ -488,3 +527,5 @@ enum vm_instruction_error_number { }; #endif + +#endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e5652d97..8d7a619718b5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 38e4894165b9..db917ec89040 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2347,6 +2347,27 @@ int uncore_pmu_event_init(struct perf_event *event) return ret; } +static ssize_t uncore_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask); + + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -2384,8 +2405,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) free_percpu(type->pmus[i].box); kfree(type->pmus); type->pmus = NULL; - kfree(type->attr_groups[1]); - type->attr_groups[1] = NULL; + kfree(type->events_group); + type->events_group = NULL; } static void __init uncore_types_exit(struct intel_uncore_type **types) @@ -2437,9 +2458,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type) for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->attr_groups[1] = events_group; + type->events_group = events_group; } + type->pmu_group = &uncore_pmu_attr_group; type->pmus = pmus; return 0; fail: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 5b81c1856aac..e68a4550e952 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -369,10 +369,12 @@ struct intel_uncore_type { struct intel_uncore_pmu *pmus; struct intel_uncore_ops *ops; struct uncore_event_desc *event_descs; - const struct attribute_group *attr_groups[3]; + const struct attribute_group *attr_groups[4]; }; -#define format_group attr_groups[0] +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 623f28837476..f438a44bf8f9 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1109,17 +1109,21 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx + leal function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax +ftrace_ret: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -1131,6 +1135,71 @@ ftrace_stub: ret END(ftrace_caller) +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + +ftrace_restore_flags: + popf + jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) @@ -1171,9 +1240,6 @@ END(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1a8f3cbb6ee3..4f0322e4ecee 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -69,25 +69,51 @@ .section .entry.text, "ax" #ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(mcount) + +ENTRY(function_hook) retq -END(mcount) +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + leaq function_trace_op, %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ cmpl $0, function_trace_stop jne ftrace_stub - MCOUNT_SAVE_FRAME - - movq 0x38(%rsp), %rdi - movq 8(%rbp), %rsi - subq $MCOUNT_INSN_SIZE, %rdi + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub MCOUNT_RESTORE_FRAME +ftrace_return: #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -98,8 +124,78 @@ GLOBAL(ftrace_stub) retq END(ftrace_caller) +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(mcount) + +ENTRY(function_hook) cmpl $0, function_trace_stop jne ftrace_stub @@ -120,8 +216,12 @@ GLOBAL(ftrace_stub) trace: MCOUNT_SAVE_FRAME - movq 0x38(%rsp), %rdi + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else movq 8(%rbp), %rsi +#endif subq $MCOUNT_INSN_SIZE, %rdi call *ftrace_trace_function @@ -129,20 +229,22 @@ trace: MCOUNT_RESTORE_FRAME jmp ftrace_stub -END(mcount) +END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - MCOUNT_SAVE_FRAME +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else leaq 8(%rbp), %rdi - movq 0x38(%rsp), %rsi movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi subq $MCOUNT_INSN_SIZE, %rsi call prepare_ftrace_return diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4bf6e6..1d414029f1d8 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -206,6 +206,21 @@ static int ftrace_modify_code(unsigned long ip, unsigned const char *old_code, unsigned const char *new_code); +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func) ret = ftrace_modify_code(ip, old, new); + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + } + atomic_dec(&modifying_ftrace_code); return ret; @@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } +/* + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + */ +static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/* + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + */ +static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; @@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + ftrace_addr = get_ftrace_old_addr(rec); + /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) + goto update; + + /* Check both ftrace_addr and ftrace_old_addr */ + ftrace_addr = get_ftrace_old_addr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } + update: return probe_kernel_write((void *)ip, &nop[0], 1); } @@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return add_update_call(rec, ftrace_addr); @@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return finish_update_call(rec, ftrace_addr); diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index e2f751efb7b1..57916c0d3cf6 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +#ifdef KPROBES_CAN_USE_FTRACE +static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); +} +#endif + /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { +#ifdef KPROBES_CAN_USE_FTRACE + if (kprobe_ftrace(p)) { + skip_singlestep(p, regs, kcb); + return 1; + } +#endif setup_singlestep(p, regs, kcb, 0); return 1; } @@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } +#ifdef KPROBES_CAN_USE_FTRACE +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} +#endif + int __init arch_init_kprobes(void) { return arch_init_optprobes(); diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c new file mode 100644 index 000000000000..e309cc5c276e --- /dev/null +++ b/arch/x86/kernel/perf_regs.c @@ -0,0 +1,105 @@ +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <linux/stddef.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_X86_32 +#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX +#else +#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX +#endif + +#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) + +static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { + PT_REGS_OFFSET(PERF_REG_X86_AX, ax), + PT_REGS_OFFSET(PERF_REG_X86_BX, bx), + PT_REGS_OFFSET(PERF_REG_X86_CX, cx), + PT_REGS_OFFSET(PERF_REG_X86_DX, dx), + PT_REGS_OFFSET(PERF_REG_X86_SI, si), + PT_REGS_OFFSET(PERF_REG_X86_DI, di), + PT_REGS_OFFSET(PERF_REG_X86_BP, bp), + PT_REGS_OFFSET(PERF_REG_X86_SP, sp), + PT_REGS_OFFSET(PERF_REG_X86_IP, ip), + PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags), + PT_REGS_OFFSET(PERF_REG_X86_CS, cs), + PT_REGS_OFFSET(PERF_REG_X86_SS, ss), +#ifdef CONFIG_X86_32 + PT_REGS_OFFSET(PERF_REG_X86_DS, ds), + PT_REGS_OFFSET(PERF_REG_X86_ES, es), + PT_REGS_OFFSET(PERF_REG_X86_FS, fs), + PT_REGS_OFFSET(PERF_REG_X86_GS, gs), +#else + /* + * The pt_regs struct does not store + * ds, es, fs, gs in 64 bit mode. + */ + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, +#endif +#ifdef CONFIG_X86_64 + PT_REGS_OFFSET(PERF_REG_X86_R8, r8), + PT_REGS_OFFSET(PERF_REG_X86_R9, r9), + PT_REGS_OFFSET(PERF_REG_X86_R10, r10), + PT_REGS_OFFSET(PERF_REG_X86_R11, r11), + PT_REGS_OFFSET(PERF_REG_X86_R12, r12), + PT_REGS_OFFSET(PERF_REG_X86_R13, r13), + PT_REGS_OFFSET(PERF_REG_X86_R14, r14), + PT_REGS_OFFSET(PERF_REG_X86_R15, r15), +#endif +}; + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) + return 0; + + return regs_get_register(regs, pt_regs_offset[idx]); +} + +#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) + +#ifdef CONFIG_X86_32 +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} +#else /* CONFIG_X86_64 */ +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + if (mask & REG_NOSUPPORT) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_IA32)) + return PERF_SAMPLE_REGS_ABI_32; + else + return PERF_SAMPLE_REGS_ABI_64; +} +#endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index c346d1161488..cd3b2438a980 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child) return 1; } +void set_task_blockstep(struct task_struct *task, bool on) +{ + unsigned long debugctl; + + /* + * Ensure irq/preemption can't change debugctl in between. + * Note also that both TIF_BLOCKSTEP and debugctl should + * be changed atomically wrt preemption. + * FIXME: this means that set/clear TIF_BLOCKSTEP is simply + * wrong if task != current, SIGKILL can wakeup the stopped + * tracee and set/clear can play with the running task, this + * can confuse the next __switch_to_xtra(). + */ + local_irq_disable(); + debugctl = get_debugctlmsr(); + if (on) { + debugctl |= DEBUGCTLMSR_BTF; + set_tsk_thread_flag(task, TIF_BLOCKSTEP); + } else { + debugctl &= ~DEBUGCTLMSR_BTF; + clear_tsk_thread_flag(task, TIF_BLOCKSTEP); + } + if (task == current) + update_debugctlmsr(debugctl); + local_irq_enable(); +} + /* * Enable single or block step. */ @@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block) * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ - if (enable_single_step(child) && block) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - set_tsk_thread_flag(child, TIF_BLOCKSTEP); - } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (enable_single_step(child) && block) + set_task_blockstep(child, true); + else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); } void user_enable_single_step(struct task_struct *child) @@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child) /* * Make sure block stepping (BTF) is disabled. */ - if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); - clear_tsk_thread_flag(child, TIF_BLOCKSTEP); - } + if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) + set_task_blockstep(child, false); /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 36fd42091fa7..9538f00827a9 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -41,6 +41,9 @@ /* Adjust the return address of a call insn */ #define UPROBE_FIX_CALL 0x2 +/* Instruction will modify TF, don't change it */ +#define UPROBE_FIX_SETF 0x4 + #define UPROBE_FIX_RIP_AX 0x8000 #define UPROBE_FIX_RIP_CX 0x4000 @@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) insn_get_opcode(insn); /* should be a nop */ switch (OPCODE1(insn)) { + case 0x9d: + /* popf */ + auprobe->fixups |= UPROBE_FIX_SETF; + break; case 0xc3: /* ret/lret */ case 0xcb: case 0xc2: @@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) * Skip these instructions as per the currently known x86 ISA. * 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 } */ -bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { int i; @@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) } return false; } + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + bool ret = __skip_sstep(auprobe, regs); + if (ret && (regs->flags & X86_EFLAGS_TF)) + send_sig(SIGTRAP, current, 0); + return ret; +} + +void arch_uprobe_enable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + struct pt_regs *regs = task_pt_regs(task); + + autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); + + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(task, TIF_BLOCKSTEP)) + set_task_blockstep(task, false); +} + +void arch_uprobe_disable_step(struct arch_uprobe *auprobe) +{ + struct task_struct *task = current; + struct arch_uprobe_task *autask = &task->utask->autask; + bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED); + struct pt_regs *regs = task_pt_regs(task); + /* + * The state of TIF_BLOCKSTEP was not saved so we can get an extra + * SIGTRAP if we do not clear TF. We need to examine the opcode to + * make it right. + */ + if (unlikely(trapped)) { + if (!autask->saved_tf) + regs->flags &= ~X86_EFLAGS_TF; + } else { + if (autask->saved_tf) + send_sig(SIGTRAP, task, 0); + else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + regs->flags &= ~X86_EFLAGS_TF; + } +} diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 6020f6f5927c..1330dd102950 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -13,9 +13,13 @@ #include <asm/ftrace.h> #ifdef CONFIG_FUNCTION_TRACER -/* mcount is defined in assembly */ +/* mcount and __fentry__ are defined in assembly */ +#ifdef CC_USING_FENTRY +EXPORT_SYMBOL(__fentry__); +#else EXPORT_SYMBOL(mcount); #endif +#endif EXPORT_SYMBOL(__get_user_1); EXPORT_SYMBOL(__get_user_2); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a71faf727ff3..bca63f04dccb 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -183,95 +183,6 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 -#define VMX_EXIT_REASONS \ - { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ - { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ - { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ - { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ - { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ - { EXIT_REASON_CPUID, "CPUID" }, \ - { EXIT_REASON_HLT, "HLT" }, \ - { EXIT_REASON_INVLPG, "INVLPG" }, \ - { EXIT_REASON_RDPMC, "RDPMC" }, \ - { EXIT_REASON_RDTSC, "RDTSC" }, \ - { EXIT_REASON_VMCALL, "VMCALL" }, \ - { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ - { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ - { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ - { EXIT_REASON_VMPTRST, "VMPTRST" }, \ - { EXIT_REASON_VMREAD, "VMREAD" }, \ - { EXIT_REASON_VMRESUME, "VMRESUME" }, \ - { EXIT_REASON_VMWRITE, "VMWRITE" }, \ - { EXIT_REASON_VMOFF, "VMOFF" }, \ - { EXIT_REASON_VMON, "VMON" }, \ - { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ - { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ - { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ - { EXIT_REASON_MSR_READ, "MSR_READ" }, \ - { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ - { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ - { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ - { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ - { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ - { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ - { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ - { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ - { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ - { EXIT_REASON_WBINVD, "WBINVD" } - -#define SVM_EXIT_REASONS \ - { SVM_EXIT_READ_CR0, "read_cr0" }, \ - { SVM_EXIT_READ_CR3, "read_cr3" }, \ - { SVM_EXIT_READ_CR4, "read_cr4" }, \ - { SVM_EXIT_READ_CR8, "read_cr8" }, \ - { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ - { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ - { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ - { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ - { SVM_EXIT_READ_DR0, "read_dr0" }, \ - { SVM_EXIT_READ_DR1, "read_dr1" }, \ - { SVM_EXIT_READ_DR2, "read_dr2" }, \ - { SVM_EXIT_READ_DR3, "read_dr3" }, \ - { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ - { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ - { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ - { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ - { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ - { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ - { SVM_EXIT_INTR, "interrupt" }, \ - { SVM_EXIT_NMI, "nmi" }, \ - { SVM_EXIT_SMI, "smi" }, \ - { SVM_EXIT_INIT, "init" }, \ - { SVM_EXIT_VINTR, "vintr" }, \ - { SVM_EXIT_CPUID, "cpuid" }, \ - { SVM_EXIT_INVD, "invd" }, \ - { SVM_EXIT_HLT, "hlt" }, \ - { SVM_EXIT_INVLPG, "invlpg" }, \ - { SVM_EXIT_INVLPGA, "invlpga" }, \ - { SVM_EXIT_IOIO, "io" }, \ - { SVM_EXIT_MSR, "msr" }, \ - { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ - { SVM_EXIT_SHUTDOWN, "shutdown" }, \ - { SVM_EXIT_VMRUN, "vmrun" }, \ - { SVM_EXIT_VMMCALL, "hypercall" }, \ - { SVM_EXIT_VMLOAD, "vmload" }, \ - { SVM_EXIT_VMSAVE, "vmsave" }, \ - { SVM_EXIT_STGI, "stgi" }, \ - { SVM_EXIT_CLGI, "clgi" }, \ - { SVM_EXIT_SKINIT, "skinit" }, \ - { SVM_EXIT_WBINVD, "wbinvd" }, \ - { SVM_EXIT_MONITOR, "monitor" }, \ - { SVM_EXIT_MWAIT, "mwait" }, \ - { SVM_EXIT_XSETBV, "xsetbv" }, \ - { SVM_EXIT_NPF, "npf" } - /* * Tracepoint for kvm guest exit: */ diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index b8ef8ddcc292..8aa73fac6ad4 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -451,14 +451,9 @@ static void wq_sync_buffer(struct work_struct *work) { struct oprofile_cpu_buffer *b = container_of(work, struct oprofile_cpu_buffer, work.work); - if (b->cpu != smp_processor_id()) { - printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n", - smp_processor_id(), b->cpu); - - if (!cpu_online(b->cpu)) { - cancel_delayed_work(&b->work); - return; - } + if (b->cpu != smp_processor_id() && !cpu_online(b->cpu)) { + cancel_delayed_work(&b->work); + return; } sync_buffer(b->cpu); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 55e6d63d46d0..a52f2f4fe030 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -10,6 +10,7 @@ #include <linux/kallsyms.h> #include <linux/linkage.h> #include <linux/bitops.h> +#include <linux/ptrace.h> #include <linux/ktime.h> #include <linux/sched.h> #include <linux/types.h> @@ -18,6 +19,28 @@ #include <asm/ftrace.h> +/* + * If the arch supports passing the variable contents of + * function_trace_op as the third parameter back from the + * mcount call, then the arch should define this as 1. + */ +#ifndef ARCH_SUPPORTS_FTRACE_OPS +#define ARCH_SUPPORTS_FTRACE_OPS 0 +#endif + +/* + * If the arch's mcount caller does not support all of ftrace's + * features, then it must call an indirect function that + * does. Or at least does enough to prevent any unwelcomed side effects. + */ +#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \ + !ARCH_SUPPORTS_FTRACE_OPS +# define FTRACE_FORCE_LIST_FUNC 1 +#else +# define FTRACE_FORCE_LIST_FUNC 0 +#endif + + struct module; struct ftrace_hash; @@ -29,7 +52,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); +struct ftrace_ops; + +typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); /* * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are @@ -45,12 +71,33 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); * could be controled by following calls: * ftrace_function_local_enable * ftrace_function_local_disable + * SAVE_REGS - The ftrace_ops wants regs saved at each function called + * and passed to the callback. If this flag is set, but the + * architecture does not support passing regs + * (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the + * ftrace_ops will fail to register, unless the next flag + * is set. + * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the + * handler can handle an arch that does not save regs + * (the handler tests if regs == NULL), then it can set + * this flag instead. It will not fail registering the ftrace_ops + * but, the regs field will be NULL if the arch does not support + * passing regs to the handler. + * Note, if this flag is set, the SAVE_REGS flag will automatically + * get set upon registering the ftrace_ops, if the arch supports it. + * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure + * that the call back has its own recursion protection. If it does + * not set this, then the ftrace infrastructure will add recursion + * protection for the caller. */ enum { - FTRACE_OPS_FL_ENABLED = 1 << 0, - FTRACE_OPS_FL_GLOBAL = 1 << 1, - FTRACE_OPS_FL_DYNAMIC = 1 << 2, - FTRACE_OPS_FL_CONTROL = 1 << 3, + FTRACE_OPS_FL_ENABLED = 1 << 0, + FTRACE_OPS_FL_GLOBAL = 1 << 1, + FTRACE_OPS_FL_DYNAMIC = 1 << 2, + FTRACE_OPS_FL_CONTROL = 1 << 3, + FTRACE_OPS_FL_SAVE_REGS = 1 << 4, + FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, + FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, }; struct ftrace_ops { @@ -163,7 +210,8 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) return *this_cpu_ptr(ops->disabled); } -extern void ftrace_stub(unsigned long a0, unsigned long a1); +extern void ftrace_stub(unsigned long a0, unsigned long a1, + struct ftrace_ops *op, struct pt_regs *regs); #else /* !CONFIG_FUNCTION_TRACER */ /* @@ -172,6 +220,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1); */ #define register_ftrace_function(ops) ({ 0; }) #define unregister_ftrace_function(ops) ({ 0; }) +static inline int ftrace_nr_registered_ops(void) +{ + return 0; +} static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } static inline void ftrace_stop(void) { } @@ -227,12 +279,33 @@ extern void unregister_ftrace_function_probe_all(char *glob); extern int ftrace_text_reserved(void *start, void *end); +extern int ftrace_nr_registered_ops(void); + +/* + * The dyn_ftrace record's flags field is split into two parts. + * the first part which is '0-FTRACE_REF_MAX' is a counter of + * the number of callbacks that have registered the function that + * the dyn_ftrace descriptor represents. + * + * The second part is a mask: + * ENABLED - the function is being traced + * REGS - the record wants the function to save regs + * REGS_EN - the function is set up to save regs. + * + * 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 + * 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. + */ enum { - FTRACE_FL_ENABLED = (1 << 30), + FTRACE_FL_ENABLED = (1UL << 29), + FTRACE_FL_REGS = (1UL << 30), + FTRACE_FL_REGS_EN = (1UL << 31) }; -#define FTRACE_FL_MASK (0x3UL << 30) -#define FTRACE_REF_MAX ((1 << 30) - 1) +#define FTRACE_FL_MASK (0x7UL << 29) +#define FTRACE_REF_MAX ((1UL << 29) - 1) struct dyn_ftrace { union { @@ -244,6 +317,8 @@ struct dyn_ftrace { }; int ftrace_force_update(void); +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -263,9 +338,23 @@ enum { FTRACE_STOP_FUNC_RET = (1 << 4), }; +/* + * The FTRACE_UPDATE_* enum is used to pass information back + * from the ftrace_update_record() and ftrace_test_record() + * functions. These are called by the code update routines + * to find out what is to be done for a given function. + * + * IGNORE - The function is already what we want it to be + * MAKE_CALL - Start tracing the function + * MODIFY_CALL - Stop saving regs for the function + * MODIFY_CALL_REGS - Start saving regs for the function + * MAKE_NOP - Stop tracing the function + */ enum { FTRACE_UPDATE_IGNORE, FTRACE_UPDATE_MAKE_CALL, + FTRACE_UPDATE_MODIFY_CALL, + FTRACE_UPDATE_MODIFY_CALL_REGS, FTRACE_UPDATE_MAKE_NOP, }; @@ -317,7 +406,9 @@ extern int ftrace_dyn_arch_init(void *data); extern void ftrace_replace_code(int enable); extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); +extern void ftrace_regs_caller(void); extern void ftrace_call(void); +extern void ftrace_regs_call(void); extern void mcount_call(void); void ftrace_modify_all_code(int command); @@ -325,6 +416,15 @@ void ftrace_modify_all_code(int command); #ifndef FTRACE_ADDR #define FTRACE_ADDR ((unsigned long)ftrace_caller) #endif + +#ifndef FTRACE_REGS_ADDR +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller) +#else +# define FTRACE_REGS_ADDR FTRACE_ADDR +#endif +#endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_caller(void); extern int ftrace_enable_ftrace_graph_caller(void); @@ -380,6 +480,39 @@ extern int ftrace_make_nop(struct module *mod, */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +/** + * ftrace_modify_call - convert from one addr to another (no nop) + * @rec: the mcount call site record + * @old_addr: the address expected to be currently called to + * @addr: the address to change to + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should be a caller to @old_addr + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr); +#else +/* Should never be called */ +static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + return -EINVAL; +} +#endif + /* May be defined in arch */ extern int ftrace_arch_read_dyn_info(char *buf, int size); @@ -387,7 +520,7 @@ extern int skip_trace(unsigned long ip); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); -#else +#else /* CONFIG_DYNAMIC_FTRACE */ static inline int skip_trace(unsigned long ip) { return 0; } static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } @@ -405,6 +538,10 @@ static inline int ftrace_text_reserved(void *start, void *end) { return 0; } +static inline unsigned long ftrace_location(unsigned long ip) +{ + return 0; +} /* * Again users of functions that have ftrace_ops may not @@ -413,6 +550,7 @@ static inline int ftrace_text_reserved(void *start, void *end) */ #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) +#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b6e1f8c00577..23755ba42abc 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -38,6 +38,7 @@ #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> +#include <linux/ftrace.h> #ifdef CONFIG_KPROBES #include <asm/kprobes.h> @@ -48,14 +49,26 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 +/* + * If function tracer is enabled and the arch supports full + * passing of pt_regs to function tracing, then kprobes can + * optimize on top of function tracing. + */ +#if defined(CONFIG_FUNCTION_TRACER) && defined(ARCH_SUPPORTS_FTRACE_SAVE_REGS) \ + && defined(ARCH_SUPPORTS_KPROBES_ON_FTRACE) +# define KPROBES_CAN_USE_FTRACE +#endif + /* 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; @@ -128,6 +141,7 @@ struct kprobe { * NOTE: * this flag is only for optimized_kprobe. */ +#define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ /* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) @@ -146,6 +160,13 @@ static inline int kprobe_optimized(struct kprobe *p) { return p->flags & KPROBE_FLAG_OPTIMIZED; } + +/* Is this kprobe uses ftrace ? */ +static inline int kprobe_ftrace(struct kprobe *p) +{ + return p->flags & KPROBE_FLAG_FTRACE; +} + /* * Special probe type that uses setjmp-longjmp type tricks to resume * execution at a specified entry with a matching prototype corresponding @@ -295,6 +316,12 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, #endif #endif /* CONFIG_OPTPROBES */ +#ifdef KPROBES_CAN_USE_FTRACE +extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs); +extern int arch_prepare_kprobe_ftrace(struct kprobe *p); +#endif + /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index bdb41612bfec..599afc4bb67e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -130,8 +130,10 @@ enum perf_event_sample_format { PERF_SAMPLE_STREAM_ID = 1U << 9, PERF_SAMPLE_RAW = 1U << 10, PERF_SAMPLE_BRANCH_STACK = 1U << 11, + PERF_SAMPLE_REGS_USER = 1U << 12, + PERF_SAMPLE_STACK_USER = 1U << 13, - PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */ }; /* @@ -163,6 +165,15 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_HV) /* + * Values to determine ABI of the registers dump. + */ +enum perf_sample_regs_abi { + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, +}; + +/* * The format of the data returned by read() on a perf event fd, * as specified by attr.read_format: * @@ -194,6 +205,8 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ + /* add: sample_stack_user */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -255,7 +268,10 @@ struct perf_event_attr { exclude_host : 1, /* don't count in host */ exclude_guest : 1, /* don't count in guest */ - __reserved_1 : 43; + exclude_callchain_kernel : 1, /* exclude kernel callchains */ + exclude_callchain_user : 1, /* exclude user callchains */ + + __reserved_1 : 41; union { __u32 wakeup_events; /* wakeup every n events */ @@ -271,7 +287,21 @@ struct perf_event_attr { __u64 bp_len; __u64 config2; /* extension of config1 */ }; - __u64 branch_sample_type; /* enum branch_sample_type */ + __u64 branch_sample_type; /* enum perf_branch_sample_type */ + + /* + * Defines set of user regs to dump on samples. + * See asm/perf_regs.h for details. + */ + __u64 sample_regs_user; + + /* + * Defines size of the user stack to dump on samples. + */ + __u32 sample_stack_user; + + /* Align to u64. */ + __u32 __reserved_2; }; #define perf_flags(attr) (*(&(attr)->read_format + 1)) @@ -550,6 +580,13 @@ enum perf_event_type { * char data[size];}&& PERF_SAMPLE_RAW * * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK + * + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * }; */ PERF_RECORD_SAMPLE = 9, @@ -611,6 +648,7 @@ struct perf_guest_info_callbacks { #include <linux/static_key.h> #include <linux/atomic.h> #include <linux/sysfs.h> +#include <linux/perf_regs.h> #include <asm/local.h> struct perf_callchain_entry { @@ -656,6 +694,11 @@ struct perf_branch_stack { struct perf_branch_entry entries[0]; }; +struct perf_regs_user { + __u64 abi; + struct pt_regs *regs; +}; + struct task_struct; /* @@ -1135,6 +1178,8 @@ 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; + u64 stack_user_size; }; static inline void perf_sample_data_init(struct perf_sample_data *data, @@ -1144,7 +1189,10 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->addr = addr; data->raw = NULL; data->br_stack = NULL; - data->period = period; + data->period = period; + data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE; + data->regs_user.regs = NULL; + data->stack_user_size = 0; } extern void perf_output_sample(struct perf_output_handle *handle, @@ -1292,8 +1340,10 @@ static inline bool has_branch_stack(struct perf_event *event) extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); -extern void perf_output_copy(struct perf_output_handle *handle, +extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); +extern unsigned int perf_output_skip(struct perf_output_handle *handle, + unsigned int len); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern void perf_event_enable(struct perf_event *event); diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h new file mode 100644 index 000000000000..3c73d5fe18be --- /dev/null +++ b/include/linux/perf_regs.h @@ -0,0 +1,25 @@ +#ifndef _LINUX_PERF_REGS_H +#define _LINUX_PERF_REGS_H + +#ifdef CONFIG_HAVE_PERF_REGS +#include <asm/perf_regs.h> +u64 perf_reg_value(struct pt_regs *regs, int idx); +int perf_reg_validate(u64 mask); +u64 perf_reg_abi(struct task_struct *task); +#else +static inline u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + return 0; +} + +static inline int perf_reg_validate(u64 mask) +{ + return mask ? -ENOSYS : 0; +} + +static inline u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_NONE; +} +#endif /* CONFIG_HAVE_PERF_REGS */ +#endif /* _LINUX_PERF_REGS_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 335720a1fc33..83035269e597 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -446,6 +446,9 @@ extern int get_dumpable(struct mm_struct *mm); #define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ #define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ + #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) struct sighand_struct { diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index efe4b3308c74..e6f0331e3d45 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -99,25 +99,27 @@ struct xol_area { struct uprobes_state { struct xol_area *xol_area; - atomic_t count; }; + 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, bool verify); +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 int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); +extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm); extern void uprobe_free_utask(struct task_struct *t); extern void uprobe_copy_process(struct task_struct *t); extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs); +extern void __weak arch_uprobe_enable_step(struct arch_uprobe *arch); +extern void __weak arch_uprobe_disable_step(struct arch_uprobe *arch); extern int uprobe_post_sstep_notifier(struct pt_regs *regs); extern int uprobe_pre_sstep_notifier(struct pt_regs *regs); extern void uprobe_notify_resume(struct pt_regs *regs); extern bool uprobe_deny_signal(void); extern bool __weak arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs); extern void uprobe_clear_state(struct mm_struct *mm); -extern void uprobe_reset_state(struct mm_struct *mm); #else /* !CONFIG_UPROBES */ struct uprobes_state { }; @@ -138,6 +140,10 @@ static inline void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } +static inline void +uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) +{ +} static inline void uprobe_notify_resume(struct pt_regs *regs) { } @@ -158,8 +164,5 @@ static inline void uprobe_copy_process(struct task_struct *t) static inline void uprobe_clear_state(struct mm_struct *mm) { } -static inline void uprobe_reset_state(struct mm_struct *mm) -{ -} #endif /* !CONFIG_UPROBES */ #endif /* _LINUX_UPROBES_H */ diff --git a/kernel/Makefile b/kernel/Makefile index e5602d32acb3..5404911eaee9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -97,7 +97,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ -obj-$(CONFIG_X86_DS) += trace/ +obj-$(CONFIG_TRACE_CLOCK) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 98d4597f43d6..c77206184b8b 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -159,6 +159,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) int rctx; struct perf_callchain_entry *entry; + int kernel = !event->attr.exclude_callchain_kernel; + int user = !event->attr.exclude_callchain_user; + + if (!kernel && !user) + return NULL; entry = get_callchain_entry(&rctx); if (rctx == -1) @@ -169,24 +174,29 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) entry->nr = 0; - if (!user_mode(regs)) { + if (kernel && !user_mode(regs)) { perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; } - if (regs) { - /* - * Disallow cross-task user callchains. - */ - if (event->ctx->task && event->ctx->task != current) - goto exit_put; - - perf_callchain_store(entry, PERF_CONTEXT_USER); - perf_callchain_user(entry, regs); + if (user) { + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + /* + * Disallow cross-task user callchains. + */ + if (event->ctx->task && event->ctx->task != current) + goto exit_put; + + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_user(entry, regs); + } } exit_put: diff --git a/kernel/events/core.c b/kernel/events/core.c index 7fee567153f0..7b9df353ba1b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -36,6 +36,7 @@ #include <linux/perf_event.h> #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> +#include <linux/mm_types.h> #include "internal.h" @@ -3764,6 +3765,132 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); +static void +perf_output_sample_regs(struct perf_output_handle *handle, + struct pt_regs *regs, u64 mask) +{ + int bit; + + for_each_set_bit(bit, (const unsigned long *) &mask, + sizeof(mask) * BITS_PER_BYTE) { + u64 val; + + val = perf_reg_value(regs, bit); + perf_output_put(handle, val); + } +} + +static void perf_sample_regs_user(struct perf_regs_user *regs_user, + struct pt_regs *regs) +{ + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + regs_user->regs = regs; + regs_user->abi = perf_reg_abi(current); + } +} + +/* + * Get remaining task size from user stack pointer. + * + * It'd be better to take stack vma map and limit this more + * precisly, but there's no way to get it safely under interrupt, + * so using TASK_SIZE as limit. + */ +static u64 perf_ustack_task_size(struct pt_regs *regs) +{ + unsigned long addr = perf_user_stack_pointer(regs); + + if (!addr || addr >= TASK_SIZE) + return 0; + + return TASK_SIZE - addr; +} + +static u16 +perf_sample_ustack_size(u16 stack_size, u16 header_size, + struct pt_regs *regs) +{ + u64 task_size; + + /* No regs, no stack pointer, no dump. */ + if (!regs) + return 0; + + /* + * Check if we fit in with the requested stack size into the: + * - TASK_SIZE + * If we don't, we limit the size to the TASK_SIZE. + * + * - remaining sample size + * If we don't, we customize the stack size to + * fit in to the remaining sample size. + */ + + task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs)); + stack_size = min(stack_size, (u16) task_size); + + /* Current header size plus static size and dynamic size. */ + header_size += 2 * sizeof(u64); + + /* Do we fit in with the current stack dump size? */ + if ((u16) (header_size + stack_size) < header_size) { + /* + * If we overflow the maximum size for the sample, + * we customize the stack dump size to fit in. + */ + stack_size = USHRT_MAX - header_size - sizeof(u64); + stack_size = round_up(stack_size, sizeof(u64)); + } + + return stack_size; +} + +static void +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, + struct pt_regs *regs) +{ + /* Case of a kernel thread, nothing to dump */ + if (!regs) { + u64 size = 0; + perf_output_put(handle, size); + } else { + unsigned long sp; + unsigned int rem; + u64 dyn_size; + + /* + * We dump: + * static size + * - the size requested by user or the best one we can fit + * in to the sample max size + * data + * - user stack dump data + * dynamic size + * - the actual dumped size + */ + + /* Static size. */ + perf_output_put(handle, dump_size); + + /* Data. */ + sp = perf_user_stack_pointer(regs); + rem = __output_copy_user(handle, (void *) sp, dump_size); + dyn_size = dump_size - rem; + + perf_output_skip(handle, rem); + + /* Dynamic size. */ + perf_output_put(handle, dyn_size); + } +} + static void __perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) @@ -4024,6 +4151,28 @@ void perf_output_sample(struct perf_output_handle *handle, perf_output_put(handle, nr); } } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + u64 abi = data->regs_user.abi; + + /* + * If there are no regs to dump, notice it through + * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE). + */ + perf_output_put(handle, abi); + + if (abi) { + u64 mask = event->attr.sample_regs_user; + perf_output_sample_regs(handle, + data->regs_user.regs, + mask); + } + } + + if (sample_type & PERF_SAMPLE_STACK_USER) + perf_output_sample_ustack(handle, + data->stack_user_size, + data->regs_user.regs); } void perf_prepare_sample(struct perf_event_header *header, @@ -4075,6 +4224,49 @@ void perf_prepare_sample(struct perf_event_header *header, } header->size += size; } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + /* regs dump ABI info */ + int size = sizeof(u64); + + perf_sample_regs_user(&data->regs_user, regs); + + if (data->regs_user.regs) { + u64 mask = event->attr.sample_regs_user; + size += hweight64(mask) * sizeof(u64); + } + + header->size += size; + } + + if (sample_type & PERF_SAMPLE_STACK_USER) { + /* + * Either we need PERF_SAMPLE_STACK_USER bit to be allways + * processed as the last one or have additional check added + * in case new sample type is added, because we could eat + * up the rest of the sample size. + */ + struct perf_regs_user *uregs = &data->regs_user; + u16 stack_size = event->attr.sample_stack_user; + u16 size = sizeof(u64); + + if (!uregs->abi) + perf_sample_regs_user(uregs, regs); + + stack_size = perf_sample_ustack_size(stack_size, header->size, + uregs->regs); + + /* + * If there is something to dump, add space for the dump + * itself and for the field that tells the dynamic size, + * which is how many have been actually dumped. + */ + if (stack_size) + size += sizeof(u64) + stack_size; + + data->stack_user_size = stack_size; + header->size += size; + } } static void perf_event_output(struct perf_event *event, @@ -6151,6 +6343,28 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->branch_sample_type = mask; } } + + if (attr->sample_type & PERF_SAMPLE_REGS_USER) { + ret = perf_reg_validate(attr->sample_regs_user); + if (ret) + return ret; + } + + if (attr->sample_type & PERF_SAMPLE_STACK_USER) { + if (!arch_perf_have_user_stack_dump()) + return -ENOSYS; + + /* + * We have __u32 type for the size, but so far + * we can only use __u16 as maximum due to the + * __u16 sample size limit. + */ + if (attr->sample_stack_user >= USHRT_MAX) + ret = -EINVAL; + else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) + ret = -EINVAL; + } + out: return ret; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index a096c19f2c2a..d56a64c99a8b 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -2,6 +2,7 @@ #define _KERNEL_EVENTS_INTERNAL_H #include <linux/hardirq.h> +#include <linux/uaccess.h> /* Buffer handling */ @@ -76,30 +77,53 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb) return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } -static inline void -__output_copy(struct perf_output_handle *handle, - const void *buf, unsigned int len) +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned int \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned int len) \ +{ \ + unsigned long size, written; \ + \ + do { \ + size = min_t(unsigned long, handle->size, len); \ + \ + written = memcpy_func(handle->addr, buf, size); \ + \ + len -= written; \ + handle->addr += written; \ + buf += written; \ + handle->size -= written; \ + if (!handle->size) { \ + struct ring_buffer *rb = handle->rb; \ + \ + handle->page++; \ + handle->page &= rb->nr_pages - 1; \ + handle->addr = rb->data_pages[handle->page]; \ + handle->size = PAGE_SIZE << page_order(rb); \ + } \ + } while (len && written == size); \ + \ + return len; \ +} + +static inline int memcpy_common(void *dst, const void *src, size_t n) { - do { - unsigned long size = min_t(unsigned long, handle->size, len); - - memcpy(handle->addr, buf, size); - - len -= size; - handle->addr += size; - buf += size; - handle->size -= size; - if (!handle->size) { - struct ring_buffer *rb = handle->rb; - - handle->page++; - handle->page &= rb->nr_pages - 1; - handle->addr = rb->data_pages[handle->page]; - handle->size = PAGE_SIZE << page_order(rb); - } - } while (len); + memcpy(dst, src, n); + return n; } +DEFINE_OUTPUT_COPY(__output_copy, memcpy_common) + +#define MEMCPY_SKIP(dst, src, n) (n) + +DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP) + +#ifndef arch_perf_out_copy_user +#define arch_perf_out_copy_user __copy_from_user_inatomic +#endif + +DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) + /* Callchain handling */ extern struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs); @@ -134,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx) recursion[rctx]--; } +#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP +static inline bool arch_perf_have_user_stack_dump(void) +{ + return true; +} + +#define perf_user_stack_pointer(regs) user_stack_pointer(regs) +#else +static inline bool arch_perf_have_user_stack_dump(void) +{ + return false; +} + +#define perf_user_stack_pointer(regs) 0 +#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */ + #endif /* _KERNEL_EVENTS_INTERNAL_H */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 6ddaba43fb7a..23cb34ff3973 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -182,10 +182,16 @@ out: return -ENOSPC; } -void perf_output_copy(struct perf_output_handle *handle, +unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { - __output_copy(handle, buf, len); + return __output_copy(handle, buf, len); +} + +unsigned int perf_output_skip(struct perf_output_handle *handle, + unsigned int len) +{ + return __output_skip(handle, NULL, len); } void perf_output_end(struct perf_output_handle *handle) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c08a22d02f72..912ef48d28ab 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -280,12 +280,10 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_ if (ret <= 0) return ret; - lock_page(page); vaddr_new = kmap_atomic(page); vaddr &= ~PAGE_MASK; memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); - unlock_page(page); put_page(page); @@ -334,7 +332,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned */ result = is_swbp_at_addr(mm, vaddr); if (result == 1) - return -EEXIST; + return 0; if (result) return result; @@ -347,24 +345,22 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. - * @verify: if true, verify existance of breakpoint instruction. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak -set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify) +set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { - if (verify) { - int result; + int result; + + result = is_swbp_at_addr(mm, vaddr); + if (!result) + return -EINVAL; - result = is_swbp_at_addr(mm, vaddr); - if (!result) - return -EINVAL; + if (result != 1) + return result; - if (result != 1) - return result; - } return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn); } @@ -415,11 +411,10 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; - unsigned long flags; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); return uprobe; } @@ -466,12 +461,11 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe) */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { - unsigned long flags; struct uprobe *u; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); /* For now assume that the instruction need not be single-stepped */ uprobe->flags |= UPROBE_SKIP_SSTEP; @@ -649,6 +643,7 @@ static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr) { + bool first_uprobe; int ret; /* @@ -659,7 +654,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence behave as if probe already existed. */ if (!uprobe->consumers) - return -EEXIST; + return 0; if (!(uprobe->flags & UPROBE_COPY_INSN)) { ret = copy_insn(uprobe, vma->vm_file); @@ -681,17 +676,18 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, } /* - * Ideally, should be updating the probe count after the breakpoint - * has been successfully inserted. However a thread could hit the - * breakpoint we just inserted even before the probe count is - * incremented. If this is the first breakpoint placed, breakpoint - * notifier might ignore uprobes and pass the trap to the thread. - * Hence increment before and decrement on failure. + * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), + * the task can hit this breakpoint right after __replace_page(). */ - atomic_inc(&mm->uprobes_state.count); + first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); + if (first_uprobe) + set_bit(MMF_HAS_UPROBES, &mm->flags); + ret = set_swbp(&uprobe->arch, mm, vaddr); - if (ret) - atomic_dec(&mm->uprobes_state.count); + if (!ret) + clear_bit(MMF_RECALC_UPROBES, &mm->flags); + else if (first_uprobe) + clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } @@ -699,8 +695,12 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, static void remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, vaddr, true)) - atomic_dec(&mm->uprobes_state.count); + /* can happen if uprobe_register() fails */ + if (!test_bit(MMF_HAS_UPROBES, &mm->flags)) + return; + + set_bit(MMF_RECALC_UPROBES, &mm->flags); + set_orig_insn(&uprobe->arch, mm, vaddr); } /* @@ -710,11 +710,9 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad */ static void delete_uprobe(struct uprobe *uprobe) { - unsigned long flags; - - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); iput(uprobe->inode); put_uprobe(uprobe); atomic_dec(&uprobe_events); @@ -831,17 +829,11 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; - if (is_register) { + if (is_register) err = install_breakpoint(uprobe, mm, vma, info->vaddr); - /* - * We can race against uprobe_mmap(), see the - * comment near uprobe_hash(). - */ - if (err == -EEXIST) - err = 0; - } else { + else remove_breakpoint(uprobe, mm, info->vaddr); - } + unlock: up_write(&mm->mmap_sem); free: @@ -908,7 +900,8 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * } mutex_unlock(uprobes_hash(inode)); - put_uprobe(uprobe); + if (uprobe) + put_uprobe(uprobe); return ret; } @@ -978,7 +971,6 @@ static void build_probe_list(struct inode *inode, struct list_head *head) { loff_t min, max; - unsigned long flags; struct rb_node *n, *t; struct uprobe *u; @@ -986,7 +978,7 @@ static void build_probe_list(struct inode *inode, min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { @@ -1004,27 +996,20 @@ static void build_probe_list(struct inode *inode, atomic_inc(&u->ref); } } - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); } /* - * Called from mmap_region. - * called with mm->mmap_sem acquired. + * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * - * Return -ve no if we fail to insert probes and we cannot - * bail-out. - * Return 0 otherwise. i.e: - * - * - successful insertion of probes - * - (or) no possible probes to be inserted. - * - (or) insertion of probes failed but we can bail-out. + * Currently we ignore all errors and always return 0, the callers + * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; - int ret, count; if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) return 0; @@ -1036,44 +1021,35 @@ int uprobe_mmap(struct vm_area_struct *vma) mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); - ret = 0; - count = 0; - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - if (!ret) { + if (!fatal_signal_pending(current)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); - - ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - /* - * We can race against uprobe_register(), see the - * comment near uprobe_hash(). - */ - if (ret == -EEXIST) { - ret = 0; - - if (!is_swbp_at_addr(vma->vm_mm, vaddr)) - continue; - - /* - * Unable to insert a breakpoint, but - * breakpoint lies underneath. Increment the - * probe count. - */ - atomic_inc(&vma->vm_mm->uprobes_state.count); - } - - if (!ret) - count++; + install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } - mutex_unlock(uprobes_mmap_hash(inode)); - if (ret) - atomic_sub(count, &vma->vm_mm->uprobes_state.count); + return 0; +} - return ret; +static bool +vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + loff_t min, max; + struct inode *inode; + struct rb_node *n; + + inode = vma->vm_file->f_mapping->host; + + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; + + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + spin_unlock(&uprobes_treelock); + + return !!n; } /* @@ -1081,37 +1057,18 @@ int uprobe_mmap(struct vm_area_struct *vma) */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct list_head tmp_list; - struct uprobe *uprobe, *u; - struct inode *inode; - if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; - if (!atomic_read(&vma->vm_mm->uprobes_state.count)) - return; - - inode = vma->vm_file->f_mapping->host; - if (!inode) + if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || + test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; - mutex_lock(uprobes_mmap_hash(inode)); - build_probe_list(inode, vma, start, end, &tmp_list); - - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); - /* - * An unregister could have removed the probe before - * unmap. So check before we decrement the count. - */ - if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1) - atomic_dec(&vma->vm_mm->uprobes_state.count); - put_uprobe(uprobe); - } - mutex_unlock(uprobes_mmap_hash(inode)); + if (vma_has_uprobes(vma, start, end)) + set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ @@ -1213,13 +1170,15 @@ void uprobe_clear_state(struct mm_struct *mm) kfree(area); } -/* - * uprobe_reset_state - Free the area allocated for slots. - */ -void uprobe_reset_state(struct mm_struct *mm) +void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - mm->uprobes_state.xol_area = NULL; - atomic_set(&mm->uprobes_state.count, 0); + newmm->uprobes_state.xol_area = NULL; + + if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { + set_bit(MMF_HAS_UPROBES, &newmm->flags); + /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ + set_bit(MMF_RECALC_UPROBES, &newmm->flags); + } } /* @@ -1437,6 +1396,25 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } +static void mmf_recalc_uprobes(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!valid_vma(vma, false)) + continue; + /* + * This is not strictly accurate, we can race with + * uprobe_unregister() and see the already removed + * uprobe if delete_uprobe() was not yet called. + */ + if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) + return; + } + + clear_bit(MMF_HAS_UPROBES, &mm->flags); +} + static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; @@ -1458,11 +1436,24 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) } else { *is_swbp = -EFAULT; } + + if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) + mmf_recalc_uprobes(mm); up_read(&mm->mmap_sem); return uprobe; } +void __weak arch_uprobe_enable_step(struct arch_uprobe *arch) +{ + user_enable_single_step(current); +} + +void __weak arch_uprobe_disable_step(struct arch_uprobe *arch) +{ + user_disable_single_step(current); +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1509,7 +1500,7 @@ static void handle_swbp(struct pt_regs *regs) utask->state = UTASK_SSTEP; if (!pre_ssout(uprobe, regs, bp_vaddr)) { - user_enable_single_step(current); + arch_uprobe_enable_step(&uprobe->arch); return; } @@ -1518,17 +1509,15 @@ cleanup_ret: utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; } - if (uprobe) { - if (!(uprobe->flags & UPROBE_SKIP_SSTEP)) + if (!(uprobe->flags & UPROBE_SKIP_SSTEP)) - /* - * cannot singlestep; cannot skip instruction; - * re-execute the instruction. - */ - instruction_pointer_set(regs, bp_vaddr); + /* + * cannot singlestep; cannot skip instruction; + * re-execute the instruction. + */ + instruction_pointer_set(regs, bp_vaddr); - put_uprobe(uprobe); - } + put_uprobe(uprobe); } /* @@ -1547,10 +1536,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) else WARN_ON_ONCE(1); + arch_uprobe_disable_step(&uprobe->arch); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; - user_disable_single_step(current); xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); @@ -1589,8 +1578,7 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { struct uprobe_task *utask; - if (!current->mm || !atomic_read(¤t->mm->uprobes_state.count)) - /* task is currently not uprobed */ + if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags)) return 0; utask = current->utask; diff --git a/kernel/fork.c b/kernel/fork.c index 2c8857e12855..2343c9eaaaf4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -353,6 +353,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) down_write(&oldmm->mmap_sem); flush_cache_dup_mm(oldmm); + uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ @@ -454,9 +455,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; - - if (file) - uprobe_mmap(tmp); } /* a new mm has just been created */ arch_dup_mmap(oldmm, mm); @@ -839,8 +837,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; #endif - uprobe_reset_state(mm); - if (!mm_init(mm, tsk)) goto fail_nomem; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c62b8546cc90..098f396aa409 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -561,9 +561,9 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) { LIST_HEAD(free_list); + mutex_lock(&kprobe_mutex); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); - mutex_lock(&kprobe_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) @@ -586,8 +586,8 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(&free_list); - mutex_unlock(&kprobe_mutex); mutex_unlock(&module_mutex); + mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) @@ -759,20 +759,32 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p) struct kprobe *ap; struct optimized_kprobe *op; + /* Impossible to optimize ftrace-based kprobe */ + if (kprobe_ftrace(p)) + return; + + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + mutex_lock(&text_mutex); + ap = alloc_aggr_kprobe(p); if (!ap) - return; + goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); - return; + goto out; } init_aggr_kprobe(ap, p); - optimize_kprobe(ap); + optimize_kprobe(ap); /* This just kicks optimizer thread */ + +out: + mutex_unlock(&text_mutex); + jump_label_unlock(); } #ifdef CONFIG_SYSCTL @@ -907,9 +919,64 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) } #endif /* CONFIG_OPTPROBES */ +#ifdef KPROBES_CAN_USE_FTRACE +static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { + .func = kprobe_ftrace_handler, + .flags = FTRACE_OPS_FL_SAVE_REGS, +}; +static int kprobe_ftrace_enabled; + +/* Must ensure p->addr is really on ftrace */ +static int __kprobes prepare_kprobe(struct kprobe *p) +{ + if (!kprobe_ftrace(p)) + return arch_prepare_kprobe(p); + + return arch_prepare_kprobe_ftrace(p); +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes arm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 0, 0); + WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + kprobe_ftrace_enabled++; + if (kprobe_ftrace_enabled == 1) { + ret = register_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + kprobe_ftrace_enabled--; + if (kprobe_ftrace_enabled == 0) { + ret = unregister_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 1, 0); + WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); +} +#else /* !KPROBES_CAN_USE_FTRACE */ +#define prepare_kprobe(p) arch_prepare_kprobe(p) +#define arm_kprobe_ftrace(p) do {} while (0) +#define disarm_kprobe_ftrace(p) do {} while (0) +#endif + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + if (unlikely(kprobe_ftrace(kp))) { + arm_kprobe_ftrace(kp); + return; + } /* * Here, since __arm_kprobe() doesn't use stop_machine(), * this doesn't cause deadlock on text_mutex. So, we don't @@ -921,11 +988,15 @@ static void __kprobes arm_kprobe(struct kprobe *kp) } /* Disarm a kprobe with text_mutex */ -static void __kprobes disarm_kprobe(struct kprobe *kp) +static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt) { + if (unlikely(kprobe_ftrace(kp))) { + disarm_kprobe_ftrace(kp); + return; + } /* Ditto */ mutex_lock(&text_mutex); - __disarm_kprobe(kp, true); + __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); } @@ -1144,12 +1215,6 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; - if (kprobe_disabled(ap) && !kprobe_disabled(p)) { - ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) - /* Arm the breakpoint again. */ - __arm_kprobe(ap); - } return 0; } @@ -1189,11 +1254,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, int ret = 0; struct kprobe *ap = orig_p; + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + /* + * Get online CPUs to avoid text_mutex deadlock.with stop machine, + * which is invoked by unoptimize_kprobe() in add_new_kprobe() + */ + get_online_cpus(); + mutex_lock(&text_mutex); + if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); - if (!ap) - return -ENOMEM; + if (!ap) { + ret = -ENOMEM; + goto out; + } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) /* This probe is going to die. Rescue it */ @@ -1213,7 +1289,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ - return ret; + goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); @@ -1228,7 +1304,20 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, /* Copy ap's insn slot to p */ copy_kprobe(ap, p); - return add_new_kprobe(ap, p); + ret = add_new_kprobe(ap, p); + +out: + mutex_unlock(&text_mutex); + put_online_cpus(); + jump_label_unlock(); + + if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { + ap->flags &= ~KPROBE_FLAG_DISABLED; + if (!kprobes_all_disarmed) + /* Arm the breakpoint again. */ + arm_kprobe(ap); + } + return ret; } static int __kprobes in_kprobes_functions(unsigned long addr) @@ -1313,71 +1402,96 @@ static inline int check_kprobe_rereg(struct kprobe *p) return ret; } -int __kprobes register_kprobe(struct kprobe *p) +static __kprobes int check_kprobe_address_safe(struct kprobe *p, + struct module **probed_mod) { int ret = 0; - struct kprobe *old_p; - struct module *probed_mod; - kprobe_opcode_t *addr; - - addr = kprobe_addr(p); - if (IS_ERR(addr)) - return PTR_ERR(addr); - p->addr = addr; + unsigned long ftrace_addr; - ret = check_kprobe_rereg(p); - if (ret) - return ret; + /* + * If the address is located on a ftrace nop, set the + * breakpoint to the following instruction. + */ + ftrace_addr = ftrace_location((unsigned long)p->addr); + if (ftrace_addr) { +#ifdef KPROBES_CAN_USE_FTRACE + /* Given address is not on the instruction boundary */ + if ((unsigned long)p->addr != ftrace_addr) + return -EILSEQ; + p->flags |= KPROBE_FLAG_FTRACE; +#else /* !KPROBES_CAN_USE_FTRACE */ + return -EINVAL; +#endif + } jump_label_lock(); preempt_disable(); + + /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || - ftrace_text_reserved(p->addr, p->addr) || jump_label_text_reserved(p->addr, p->addr)) { ret = -EINVAL; - goto cannot_probe; + goto out; } - /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ - p->flags &= KPROBE_FLAG_DISABLED; - - /* - * Check if are we probing a module. - */ - probed_mod = __module_text_address((unsigned long) p->addr); - if (probed_mod) { - /* Return -ENOENT if fail. */ - ret = -ENOENT; + /* Check if are we probing a module */ + *probed_mod = __module_text_address((unsigned long) p->addr); + if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ - if (unlikely(!try_module_get(probed_mod))) - goto cannot_probe; + if (unlikely(!try_module_get(*probed_mod))) { + ret = -ENOENT; + goto out; + } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ - if (within_module_init((unsigned long)p->addr, probed_mod) && - probed_mod->state != MODULE_STATE_COMING) { - module_put(probed_mod); - goto cannot_probe; + if (within_module_init((unsigned long)p->addr, *probed_mod) && + (*probed_mod)->state != MODULE_STATE_COMING) { + module_put(*probed_mod); + *probed_mod = NULL; + ret = -ENOENT; } - /* ret will be updated by following code */ } +out: preempt_enable(); jump_label_unlock(); + return ret; +} + +int __kprobes register_kprobe(struct kprobe *p) +{ + int ret; + struct kprobe *old_p; + struct module *probed_mod; + kprobe_opcode_t *addr; + + /* Adjust probe address from symbol */ + addr = kprobe_addr(p); + if (IS_ERR(addr)) + return PTR_ERR(addr); + p->addr = addr; + + ret = check_kprobe_rereg(p); + if (ret) + return ret; + + /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ + p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); - mutex_lock(&kprobe_mutex); - jump_label_lock(); /* needed to call jump_label_text_reserved() */ + ret = check_kprobe_address_safe(p, &probed_mod); + if (ret) + return ret; - get_online_cpus(); /* For avoiding text_mutex deadlock. */ - mutex_lock(&text_mutex); + mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { @@ -1386,7 +1500,9 @@ int __kprobes register_kprobe(struct kprobe *p) goto out; } - ret = arch_prepare_kprobe(p); + mutex_lock(&text_mutex); /* Avoiding text modification */ + ret = prepare_kprobe(p); + mutex_unlock(&text_mutex); if (ret) goto out; @@ -1395,26 +1511,18 @@ int __kprobes register_kprobe(struct kprobe *p) &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: - mutex_unlock(&text_mutex); - put_online_cpus(); - jump_label_unlock(); mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; - -cannot_probe: - preempt_enable(); - jump_label_unlock(); - return ret; } EXPORT_SYMBOL_GPL(register_kprobe); @@ -1451,7 +1559,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { - disarm_kprobe(orig_p); + disarm_kprobe(orig_p, true); orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -2049,10 +2157,11 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, if (!pp) pp = p; - seq_printf(pi, "%s%s%s\n", + seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), - (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); + (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), + (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -2131,14 +2240,12 @@ static void __kprobes arm_all_kprobes(void) goto already_enabled; /* Arming kprobes doesn't optimize kprobe itself */ - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); } - mutex_unlock(&text_mutex); kprobes_all_disarmed = false; printk(KERN_INFO "Kprobes globally enabled\n"); @@ -2166,15 +2273,13 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - __disarm_kprobe(p, false); + disarm_kprobe(p, false); } } - mutex_unlock(&text_mutex); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8c4c07071cc5..4cea4f41c1d9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS help See Documentation/trace/ftrace-design.txt +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + config HAVE_C_RECORDMCOUNT bool help @@ -57,8 +62,12 @@ config HAVE_C_RECORDMCOUNT config TRACER_MAX_TRACE bool +config TRACE_CLOCK + bool + config RING_BUFFER bool + select TRACE_CLOCK config FTRACE_NMI_ENTER bool @@ -109,6 +118,7 @@ config TRACING select NOP_TRACER select BINARY_PRINTF select EVENT_TRACING + select TRACE_CLOCK config GENERIC_TRACER bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index b831087c8200..d7e2068e4b71 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -5,10 +5,12 @@ ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +ifdef CONFIG_FTRACE_SELFTEST # selftest needs instrumentation CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif +endif # If unlikely tracing is enabled, do not trace these files ifdef CONFIG_TRACING_BRANCHES @@ -17,11 +19,7 @@ endif CFLAGS_trace_events_filter.o := -I$(src) -# -# Make the trace clocks available generally: it's infrastructure -# relied on by ptrace for example: -# -obj-y += trace_clock.o +obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b4f20fba09fc..9dcf15d38380 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -64,12 +64,20 @@ #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) +static struct ftrace_ops ftrace_list_end __read_mostly = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; /* Quick disabling of function tracer. */ -int function_trace_stop; +int function_trace_stop __read_mostly; + +/* Current function tracing op */ +struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* List for set_ftrace_pid's pids. */ LIST_HEAD(ftrace_pids); @@ -86,22 +94,43 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops ftrace_list_end __read_mostly = { - .func = ftrace_stub, -}; - static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; -ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#else +/* See comment below, where ftrace_ops_list_func is defined */ +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); +#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +#endif + +/** + * ftrace_nr_registered_ops - return number of ops registered + * + * Returns the number of ftrace_ops registered and tracing functions + */ +int ftrace_nr_registered_ops(void) +{ + struct ftrace_ops *ops; + int cnt = 0; + + mutex_lock(&ftrace_lock); + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) + cnt++; + + mutex_unlock(&ftrace_lock); + + return cnt; +} /* * Traverse the ftrace_global_list, invoking all entries. The reason that we @@ -112,29 +141,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_global_list_func(unsigned long ip, - unsigned long parent_ip) +static void +ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) return; trace_recursion_set(TRACE_GLOBAL_BIT); op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); /*see above*/ }; trace_recursion_clear(TRACE_GLOBAL_BIT); } -static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip); + ftrace_pid_function(ip, parent_ip, op, regs); } static void set_ftrace_pid_function(ftrace_func_t func) @@ -153,25 +182,9 @@ static void set_ftrace_pid_function(ftrace_func_t func) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; - __ftrace_trace_function = ftrace_stub; - __ftrace_trace_function_delay = ftrace_stub; ftrace_pid_function = ftrace_stub; } -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST -/* - * For those archs that do not test ftrace_trace_stop in their - * mcount call site, we need to do it from C. - */ -static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) -{ - if (function_trace_stop) - return; - - __ftrace_trace_function(ip, parent_ip); -} -#endif - static void control_ops_disable_all(struct ftrace_ops *ops) { int cpu; @@ -230,28 +243,27 @@ static void update_ftrace_function(void) /* * If we are at the end of the list and this ops is - * not dynamic, then have the mcount trampoline call - * the function directly + * recursion safe and not dynamic and the arch supports passing ops, + * then have the mcount trampoline call the function directly. */ if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && - !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && + (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) && + !FTRACE_FORCE_LIST_FUNC)) { + /* Set the ftrace_ops that the arch callback uses */ + if (ftrace_ops_list == &global_ops) + function_trace_op = ftrace_global_list; + else + function_trace_op = ftrace_ops_list; func = ftrace_ops_list->func; - else + } else { + /* Just use the default ftrace_ops */ + function_trace_op = &ftrace_list_end; func = ftrace_ops_list_func; + } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; -#else -#ifdef CONFIG_DYNAMIC_FTRACE - /* do not update till all functions have been modified */ - __ftrace_trace_function_delay = func; -#else - __ftrace_trace_function = func; -#endif - ftrace_trace_function = - (func == ftrace_stub) ? func : ftrace_test_stop_func; -#endif } static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) @@ -325,6 +337,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; +#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS + /* + * If the ftrace_ops specifies SAVE_REGS, then it only can be used + * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. + * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && + !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) + return -EINVAL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) + ops->flags |= FTRACE_OPS_FL_SAVE_REGS; +#endif + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -773,7 +799,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) } static void -function_profile_call(unsigned long ip, unsigned long parent_ip) +function_profile_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -803,7 +830,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip) #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - function_profile_call(trace->func, 0); + function_profile_call(trace->func, 0, NULL, NULL); return 1; } @@ -863,6 +890,7 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int register_ftrace_profiler(void) @@ -1045,6 +1073,7 @@ static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, .filter_hash = EMPTY_HASH, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static DEFINE_MUTEX(ftrace_regex_lock); @@ -1525,6 +1554,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags++; if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) return; + /* + * If any ops wants regs saved for this function + * then all ops will get saved regs. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) return; @@ -1616,18 +1651,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) if (enable && (rec->flags & ~FTRACE_FL_MASK)) flag = FTRACE_FL_ENABLED; + /* + * If enabling and the REGS flag does not match the REGS_EN, then + * do not ignore this record. Set flags to fail the compare against + * ENABLED. + */ + if (flag && + (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN))) + flag |= FTRACE_FL_REGS; + /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) return FTRACE_UPDATE_IGNORE; if (flag) { - if (update) + /* Save off if rec is being enabled (for return value) */ + flag ^= rec->flags & FTRACE_FL_ENABLED; + + if (update) { rec->flags |= FTRACE_FL_ENABLED; - return FTRACE_UPDATE_MAKE_CALL; + if (flag & FTRACE_FL_REGS) { + if (rec->flags & FTRACE_FL_REGS) + rec->flags |= FTRACE_FL_REGS_EN; + else + rec->flags &= ~FTRACE_FL_REGS_EN; + } + } + + /* + * If this record is being updated from a nop, then + * return UPDATE_MAKE_CALL. + * Otherwise, if the EN flag is set, then return + * UPDATE_MODIFY_CALL_REGS to tell the caller to convert + * from the non-save regs, to a save regs function. + * Otherwise, + * return UPDATE_MODIFY_CALL to tell the caller to convert + * from the save regs, to a non-save regs function. + */ + if (flag & FTRACE_FL_ENABLED) + return FTRACE_UPDATE_MAKE_CALL; + else if (rec->flags & FTRACE_FL_REGS_EN) + return FTRACE_UPDATE_MODIFY_CALL_REGS; + else + return FTRACE_UPDATE_MODIFY_CALL; } - if (update) - rec->flags &= ~FTRACE_FL_ENABLED; + if (update) { + /* If there's no more users, clear all flags */ + if (!(rec->flags & ~FTRACE_FL_MASK)) + rec->flags = 0; + else + /* Just disable the record (keep REGS state) */ + rec->flags &= ~FTRACE_FL_ENABLED; + } return FTRACE_UPDATE_MAKE_NOP; } @@ -1662,13 +1738,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + unsigned long ftrace_old_addr; unsigned long ftrace_addr; int ret; - ftrace_addr = (unsigned long)FTRACE_ADDR; - ret = ftrace_update_record(rec, enable); + if (rec->flags & FTRACE_FL_REGS) + ftrace_addr = (unsigned long)FTRACE_REGS_ADDR; + else + ftrace_addr = (unsigned long)FTRACE_ADDR; + switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; @@ -1678,6 +1758,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) case FTRACE_UPDATE_MAKE_NOP: return ftrace_make_nop(NULL, rec, ftrace_addr); + + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + if (rec->flags & FTRACE_FL_REGS) + ftrace_old_addr = (unsigned long)FTRACE_ADDR; + else + ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR; + + return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } return -1; /* unknow ftrace bug */ @@ -1882,16 +1971,6 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* - * For archs that call ftrace_test_stop_func(), we must - * wait till after we update all the function callers - * before we update the callback. This keeps different - * ops that record different functions from corrupting - * each other. - */ - __ftrace_trace_function = __ftrace_trace_function_delay; -#endif function_trace_stop--; ret = ftrace_arch_code_modify_post_process(); @@ -2441,8 +2520,9 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, "%ps", (void *)rec->ip); if (iter->flags & FTRACE_ITER_ENABLED) - seq_printf(m, " (%ld)", - rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, " (%ld)%s", + rec->flags & ~FTRACE_FL_MASK, + rec->flags & FTRACE_FL_REGS ? " R" : ""); seq_printf(m, "\n"); return 0; @@ -2790,8 +2870,8 @@ static int __init ftrace_mod_cmd_init(void) } device_initcall(ftrace_mod_cmd_init); -static void -function_trace_probe_call(unsigned long ip, unsigned long parent_ip) +static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ftrace_func_probe *entry; struct hlist_head *hhd; @@ -3162,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable) +ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +{ + struct ftrace_func_entry *entry; + + if (!ftrace_location(ip)) + return -EINVAL; + + if (remove) { + entry = ftrace_lookup_ip(hash, ip); + if (!entry) + return -ENOENT; + free_hash_entry(hash, entry); + return 0; + } + + return add_hash_entry(hash, ip); +} + +static int +ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, + unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -3192,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, ret = -EINVAL; goto out_regex_unlock; } + if (ip) { + ret = ftrace_match_addr(hash, ip, remove); + if (ret < 0) + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3208,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, return ret; } +static int +ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, + int reset, int enable) +{ + return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); +} + +/** + * ftrace_set_filter_ip - set a function to filter on in ftrace by address + * @ops - the ops to set the filter with + * @ip - the address to add to or remove from the filter. + * @remove - non zero to remove the ip from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ip is NULL, it failes to update filter. + */ +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset) +{ + return ftrace_set_addr(ops, ip, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) +{ + return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable); +} + /** * ftrace_set_filter - set a function to filter on in ftrace * @ops - the ops to set the filter with @@ -3912,6 +4047,7 @@ void __init ftrace_init(void) static struct ftrace_ops global_ops = { .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int __init ftrace_nodyn_init(void) @@ -3942,10 +4078,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ static void -ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) return; @@ -3959,7 +4094,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) while (op != &ftrace_list_end) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; @@ -3969,13 +4104,18 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +static inline void +__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; + if (function_trace_stop) + return; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) return; @@ -3988,13 +4128,39 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); trace_recursion_clear(TRACE_INTERNAL_BIT); } +/* + * Some archs only support passing ip and parent_ip. Even though + * the list function ignores the op parameter, we do not want any + * C side effects, where a function is called without the caller + * sending a third parameter. + * Archs are to support both the regs and ftrace_ops at the same time. + * If they support ftrace_ops, it is assumed they support regs. + * If call backs want to use regs, they must either check for regs + * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. + * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * An architecture can pass partial regs with ftrace_ops and still + * set the ARCH_SUPPORT_FTARCE_OPS. + */ +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, regs); +} +#else +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); +} +#endif + static void clear_ftrace_swapper(void) { struct task_struct *p; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 49491fa7daa2..b32ed0e385a5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2816,7 +2816,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable); * to the buffer after this will fail and return NULL. * * This is different than ring_buffer_record_disable() as - * it works like an on/off switch, where as the disable() verison + * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ void ring_buffer_record_off(struct ring_buffer *buffer) @@ -2839,7 +2839,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off); * ring_buffer_record_off(). * * This is different than ring_buffer_record_enable() as - * it works like an on/off switch, where as the enable() verison + * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ void ring_buffer_record_on(struct ring_buffer *buffer) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5c38c81496ce..1ec5c1dab629 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -328,7 +328,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO; + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); @@ -426,15 +426,15 @@ __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { - unsigned long threshhold; + unsigned long threshold; int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &threshhold); + ret = strict_strtoul(str, 0, &threshold); if (ret < 0) return 0; - tracing_thresh = threshhold * 1000; + tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); @@ -470,6 +470,7 @@ static const char *trace_options[] = { "overwrite", "disable_on_free", "irq-info", + "markers", NULL }; @@ -3886,6 +3887,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tracing_disabled) return -EINVAL; + if (!(trace_flags & TRACE_ITER_MARKERS)) + return -EINVAL; + if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 55e1f7f0db12..63a2da0b9a6e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -472,11 +472,11 @@ extern void trace_find_cmdline(int pid, char comm[]); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +#endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -#endif extern int ring_buffer_expanded; extern bool tracing_selftest_disabled; @@ -680,6 +680,7 @@ enum trace_iterator_flags { TRACE_ITER_OVERWRITE = 0x200000, TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, + TRACE_ITER_MARKERS = 0x1000000, }; /* diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 8a6d2ee2086c..84b1e045faba 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -258,7 +258,8 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void -perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *pt_regs) { struct ftrace_entry *entry; struct hlist_head *head; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 29111da1d100..d608d09d08c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1199,6 +1199,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return 0; } +static void event_remove(struct ftrace_event_call *call) +{ + ftrace_event_enable_disable(call, 0); + if (call->event.funcs) + __unregister_ftrace_event(&call->event); + list_del(&call->list); +} + +static int event_init(struct ftrace_event_call *call) +{ + int ret = 0; + + if (WARN_ON(!call->name)) + return -EINVAL; + + if (call->class->raw_init) { + ret = call->class->raw_init(call); + if (ret < 0 && ret != -ENOSYS) + pr_warn("Could not initialize trace events/%s\n", + call->name); + } + + return ret; +} + static int __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, const struct file_operations *id, @@ -1209,19 +1234,9 @@ __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, struct dentry *d_events; int ret; - /* The linker may leave blanks */ - if (!call->name) - return -EINVAL; - - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace events/%s\n", - call->name); - return ret; - } - } + ret = event_init(call); + if (ret < 0) + return ret; d_events = event_trace_events_dir(); if (!d_events) @@ -1272,13 +1287,10 @@ static void remove_subsystem_dir(const char *name) */ static void __trace_remove_event_call(struct ftrace_event_call *call) { - ftrace_event_enable_disable(call, 0); - if (call->event.funcs) - __unregister_ftrace_event(&call->event); - debugfs_remove_recursive(call->dir); - list_del(&call->list); + event_remove(call); trace_destroy_fields(call); destroy_preds(call); + debugfs_remove_recursive(call->dir); remove_subsystem_dir(call->class->system); } @@ -1450,15 +1462,43 @@ static __init int setup_trace_event(char *str) } __setup("trace_event=", setup_trace_event); +static __init int event_trace_enable(void) +{ + struct ftrace_event_call **iter, *call; + char *buf = bootup_event_buf; + char *token; + int ret; + + for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { + + call = *iter; + ret = event_init(call); + if (!ret) + list_add(&call->list, &ftrace_events); + } + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + ret = ftrace_set_clr_event(token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + } + return 0; +} + static __init int event_trace_init(void) { - struct ftrace_event_call **call; + struct ftrace_event_call *call; struct dentry *d_tracer; struct dentry *entry; struct dentry *d_events; int ret; - char *buf = bootup_event_buf; - char *token; d_tracer = tracing_init_dentry(); if (!d_tracer) @@ -1497,24 +1537,19 @@ static __init int event_trace_init(void) if (trace_define_common_fields()) pr_warning("tracing: Failed to allocate common fields"); - for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - __trace_add_event_call(*call, NULL, &ftrace_event_id_fops, + /* + * Early initialization already enabled ftrace event. + * Now it's only necessary to create the event directory. + */ + list_for_each_entry(call, &ftrace_events, list) { + + ret = event_create_dir(call, d_events, + &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); - } - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; - if (!*token) - continue; - - ret = ftrace_set_clr_event(token, 1); - if (ret) - pr_warning("Failed to enable trace event: %s\n", token); + if (ret < 0) + event_remove(call); } ret = register_module_notifier(&trace_module_nb); @@ -1523,6 +1558,7 @@ static __init int event_trace_init(void) return 0; } +core_initcall(event_trace_enable); fs_initcall(event_trace_init); #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1646,9 +1682,11 @@ static __init void event_trace_self_tests(void) event_test_stuff(); ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0); - if (WARN_ON_ONCE(ret)) + if (WARN_ON_ONCE(ret)) { pr_warning("error disabling system %s\n", system->name); + continue; + } pr_cont("OK\n"); } @@ -1681,7 +1719,8 @@ static __init void event_trace_self_tests(void) static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static void -function_test_events_call(unsigned long ip, unsigned long parent_ip) +function_test_events_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ring_buffer_event *event; struct ring_buffer *buffer; @@ -1720,6 +1759,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static __init void event_trace_self_test_with_function(void) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 431dba8b7542..c154797a7ff7 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2002,7 +2002,7 @@ static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, static int __ftrace_function_set_filter(int filter, char *buf, int len, struct function_filter_data *data) { - int i, re_cnt, ret; + int i, re_cnt, ret = -EINVAL; int *reset; char **re; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index a426f410c060..483162a9f908 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -49,7 +49,8 @@ static void function_trace_start(struct trace_array *tr) } static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -84,7 +85,9 @@ enum { static struct tracer_flags func_flags; static void -function_trace_call(unsigned long ip, unsigned long parent_ip) +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) + { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -121,7 +124,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) } static void -function_stack_trace_call(unsigned long ip, unsigned long parent_ip) +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -164,13 +168,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct tracer_opt func_opts[] = { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ce27c8ba8d31..99b4378393d5 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, return; } -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) /* * The arch may choose to record the frame pointer used * and check it here to make sure that it is what we expect it @@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, * * Currently, x86_32 with optimize for size (-Os) makes the latest * gcc do the above. + * + * Note, -mfentry does not use frame pointers, and this test + * is not needed if CC_USING_FENTRY is set. */ if (unlikely(current->ret_stack[index].fp != frame_pointer)) { ftrace_graph_stop(); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 99d20e920368..d98ee8283b29 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -136,7 +136,8 @@ static int func_prolog_dec(struct trace_array *tr, * irqsoff uses its own tracer function to keep the overhead down: */ static void -irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; @@ -153,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ff791ea48b57..02170c00c413 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -108,7 +108,8 @@ out_enable: * wakeup uses its own tracer function to keep the overhead down: */ static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; @@ -129,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 288541f977fb..2c00a691a540 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -103,54 +103,67 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe1_cnt++; } static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe2_cnt++; } static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe3_cnt++; } static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_global_cnt++; } static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_dyn_cnt++; } static struct ftrace_ops test_probe1 = { .func = trace_selftest_test_probe1_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe2 = { .func = trace_selftest_test_probe2_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe3 = { .func = trace_selftest_test_probe3_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_global = { - .func = trace_selftest_test_global_func, - .flags = FTRACE_OPS_FL_GLOBAL, + .func = trace_selftest_test_global_func, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static void print_counts(void) @@ -393,10 +406,253 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, return ret; } + +static int trace_selftest_recursion_cnt; +static void trace_selftest_test_recursion_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * This function is registered without the recursion safe flag. + * The ftrace infrastructure should provide the recursion + * protection. If not, this will crash the kernel! + */ + trace_selftest_recursion_cnt++; + DYN_FTRACE_TEST_NAME(); +} + +static void trace_selftest_test_recursion_safe_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * We said we would provide our own recursion. By calling + * this function again, we should recurse back into this function + * and count again. But this only happens if the arch supports + * all of ftrace features and nothing else is using the function + * tracing utility. + */ + if (trace_selftest_recursion_cnt++) + return; + DYN_FTRACE_TEST_NAME(); +} + +static struct ftrace_ops test_rec_probe = { + .func = trace_selftest_test_recursion_func, +}; + +static struct ftrace_ops test_recsafe_probe = { + .func = trace_selftest_test_recursion_safe_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static int +trace_selftest_function_recursion(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int cnt; + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion: "); + + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_rec_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_rec_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 1) { + pr_cont("*callback not called once (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + trace_selftest_recursion_cnt = 1; + + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion safe: "); + + ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_recsafe_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_recsafe_probe); + + /* + * If arch supports all ftrace features, and no other task + * was on the list, we should be fine. + */ + if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) + cnt = 2; /* Should have recursed */ + else + cnt = 1; + + ret = -1; + if (trace_selftest_recursion_cnt != cnt) { + pr_cont("*callback not called expected %d times (%d)* ", + cnt, trace_selftest_recursion_cnt); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} #else # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +# define trace_selftest_function_recursion() ({ 0; }) #endif /* CONFIG_DYNAMIC_FTRACE */ +static enum { + TRACE_SELFTEST_REGS_START, + TRACE_SELFTEST_REGS_FOUND, + TRACE_SELFTEST_REGS_NOT_FOUND, +} trace_selftest_regs_stat; + +static void trace_selftest_test_regs_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + if (pt_regs) + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; + else + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; +} + +static struct ftrace_ops test_regs_probe = { + .func = trace_selftest_test_regs_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, +}; + +static int +trace_selftest_function_regs(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int supported = 0; + +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS + supported = 1; +#endif + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace regs%s: ", + !supported ? "(no arch support)" : ""); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1); + /* + * If DYNAMIC_FTRACE is not set, then we just trace all functions. + * This test really doesn't care. + */ + if (ret && ret != -ENODEV) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_regs_probe); + /* + * Now if the arch does not support passing regs, then this should + * have failed. + */ + if (!supported) { + if (!ret) { + pr_cont("*registered save-regs without arch support* "); + goto out; + } + test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED; + ret = register_ftrace_function(&test_regs_probe); + } + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_regs_probe); + + ret = -1; + + switch (trace_selftest_regs_stat) { + case TRACE_SELFTEST_REGS_START: + pr_cont("*callback never called* "); + goto out; + + case TRACE_SELFTEST_REGS_FOUND: + if (supported) + break; + pr_cont("*callback received regs without arch support* "); + goto out; + + case TRACE_SELFTEST_REGS_NOT_FOUND: + if (!supported) + break; + pr_cont("*callback received NULL regs* "); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} + /* * Simple verification test of ftrace function tracer. * Enable ftrace, sleep 1/10 second, and then read the trace @@ -442,7 +698,14 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_startup_dynamic_tracing(trace, tr, DYN_FTRACE_TEST_NAME); + if (ret) + goto out; + ret = trace_selftest_function_recursion(); + if (ret) + goto out; + + ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; @@ -778,6 +1041,8 @@ static int trace_wakeup_test_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); schedule(); + complete(x); + /* we are awake, now wait to disappear */ while (!kthread_should_stop()) { /* @@ -821,24 +1086,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* reset the max latency */ tracing_max_latency = 0; - /* sleep to let the RT thread sleep too */ - msleep(100); + while (p->on_rq) { + /* + * Sleep to make sure the RT thread is asleep too. + * On virtual machines we can't rely on timings, + * but we want to make sure this test still works. + */ + msleep(100); + } - /* - * Yes this is slightly racy. It is possible that for some - * strange reason that the RT thread we created, did not - * call schedule for 100ms after doing the completion, - * and we do a wakeup on a task that already is awake. - * But that is extremely unlikely, and the worst thing that - * happens in such a case, is that we disable tracing. - * Honestly, if this race does happen something is horrible - * wrong with the system. - */ + init_completion(&isrt); wake_up_process(p); - /* give a little time to let the thread wake up */ - msleep(100); + /* Wait for the task to wake up */ + wait_for_completion(&isrt); /* stop the tracing. */ tracing_stop(); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index d4545f49242e..0c1b165778e5 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,8 @@ static inline void check_stack(void) } static void -stack_trace_call(unsigned long ip, unsigned long parent_ip) +stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { int cpu; @@ -136,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static ssize_t diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 6b245f64c8dd..2485a7d09b11 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -487,7 +487,7 @@ int __init init_ftrace_syscalls(void) return 0; } -core_initcall(init_ftrace_syscalls); +early_initcall(init_ftrace_syscalls); #ifdef CONFIG_PERF_EVENTS diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index 54e35c1e5948..9d1421e63ff8 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -261,11 +261,13 @@ static unsigned get_mcountsym(Elf_Sym const *const sym0, &sym0[Elf_r_sym(relp)]; char const *symname = &str0[w(symp->st_name)]; char const *mcount = gpfx == '_' ? "_mcount" : "mcount"; + char const *fentry = "__fentry__"; if (symname[0] == '.') ++symname; /* ppc64 hack */ if (strcmp(mcount, symname) == 0 || - (altmcount && strcmp(altmcount, symname) == 0)) + (altmcount && strcmp(altmcount, symname) == 0) || + (strcmp(fentry, symname) == 0)) mcountsym = Elf_r_sym(relp); return mcountsym; diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 14131cb0522d..04d959fa0226 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -129,7 +129,7 @@ CFLAGS ?= -g -Wall # Append required CFLAGS override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) -override CFLAGS += $(udis86-flags) +override CFLAGS += $(udis86-flags) -D_GNU_SOURCE ifeq ($(VERBOSE),1) Q = diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5f34aa371b56..47264b4652b9 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -24,13 +24,14 @@ * Frederic Weisbecker gave his permission to relicense the code to * the Lesser General Public License. */ -#define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <string.h> #include <stdarg.h> #include <ctype.h> #include <errno.h> +#include <stdint.h> +#include <limits.h> #include "event-parse.h" #include "event-utils.h" @@ -117,14 +118,7 @@ void breakpoint(void) struct print_arg *alloc_arg(void) { - struct print_arg *arg; - - arg = malloc_or_die(sizeof(*arg)); - if (!arg) - return NULL; - memset(arg, 0, sizeof(*arg)); - - return arg; + return calloc(1, sizeof(struct print_arg)); } struct cmdline { @@ -158,7 +152,9 @@ static int cmdline_init(struct pevent *pevent) struct cmdline *cmdlines; int i; - cmdlines = malloc_or_die(sizeof(*cmdlines) * pevent->cmdline_count); + cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count); + if (!cmdlines) + return -1; i = 0; while (cmdlist) { @@ -186,8 +182,8 @@ static char *find_cmdline(struct pevent *pevent, int pid) if (!pid) return "<idle>"; - if (!pevent->cmdlines) - cmdline_init(pevent); + if (!pevent->cmdlines && cmdline_init(pevent)) + return "<not enough memory for cmdlines!>"; key.pid = pid; @@ -215,8 +211,8 @@ int pevent_pid_is_registered(struct pevent *pevent, int pid) if (!pid) return 1; - if (!pevent->cmdlines) - cmdline_init(pevent); + if (!pevent->cmdlines && cmdline_init(pevent)) + return 0; key.pid = pid; @@ -258,10 +254,14 @@ static int add_new_comm(struct pevent *pevent, const char *comm, int pid) return -1; } - cmdlines[pevent->cmdline_count].pid = pid; cmdlines[pevent->cmdline_count].comm = strdup(comm); - if (!cmdlines[pevent->cmdline_count].comm) - die("malloc comm"); + if (!cmdlines[pevent->cmdline_count].comm) { + free(cmdlines); + errno = ENOMEM; + return -1; + } + + cmdlines[pevent->cmdline_count].pid = pid; if (cmdlines[pevent->cmdline_count].comm) pevent->cmdline_count++; @@ -288,10 +288,15 @@ int pevent_register_comm(struct pevent *pevent, const char *comm, int pid) if (pevent->cmdlines) return add_new_comm(pevent, comm, pid); - item = malloc_or_die(sizeof(*item)); + item = malloc(sizeof(*item)); + if (!item) + return -1; + item->comm = strdup(comm); - if (!item->comm) - die("malloc comm"); + if (!item->comm) { + free(item); + return -1; + } item->pid = pid; item->next = pevent->cmdlist; @@ -355,7 +360,10 @@ static int func_map_init(struct pevent *pevent) struct func_map *func_map; int i; - func_map = malloc_or_die(sizeof(*func_map) * (pevent->func_count + 1)); + func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1)); + if (!func_map) + return -1; + funclist = pevent->funclist; i = 0; @@ -455,25 +463,36 @@ pevent_find_function_address(struct pevent *pevent, unsigned long long addr) int pevent_register_function(struct pevent *pevent, char *func, unsigned long long addr, char *mod) { - struct func_list *item; + struct func_list *item = malloc(sizeof(*item)); - item = malloc_or_die(sizeof(*item)); + if (!item) + return -1; item->next = pevent->funclist; item->func = strdup(func); - if (mod) + if (!item->func) + goto out_free; + + if (mod) { item->mod = strdup(mod); - else + if (!item->mod) + goto out_free_func; + } else item->mod = NULL; item->addr = addr; - if (!item->func || (mod && !item->mod)) - die("malloc func"); - pevent->funclist = item; pevent->func_count++; return 0; + +out_free_func: + free(item->func); + item->func = NULL; +out_free: + free(item); + errno = ENOMEM; + return -1; } /** @@ -524,14 +543,16 @@ static int printk_cmp(const void *a, const void *b) return 0; } -static void printk_map_init(struct pevent *pevent) +static int printk_map_init(struct pevent *pevent) { struct printk_list *printklist; struct printk_list *item; struct printk_map *printk_map; int i; - printk_map = malloc_or_die(sizeof(*printk_map) * (pevent->printk_count + 1)); + printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1)); + if (!printk_map) + return -1; printklist = pevent->printklist; @@ -549,6 +570,8 @@ static void printk_map_init(struct pevent *pevent) pevent->printk_map = printk_map; pevent->printklist = NULL; + + return 0; } static struct printk_map * @@ -557,8 +580,8 @@ find_printk(struct pevent *pevent, unsigned long long addr) struct printk_map *printk; struct printk_map key; - if (!pevent->printk_map) - printk_map_init(pevent); + if (!pevent->printk_map && printk_map_init(pevent)) + return NULL; key.addr = addr; @@ -580,21 +603,27 @@ find_printk(struct pevent *pevent, unsigned long long addr) int pevent_register_print_string(struct pevent *pevent, char *fmt, unsigned long long addr) { - struct printk_list *item; + struct printk_list *item = malloc(sizeof(*item)); - item = malloc_or_die(sizeof(*item)); + if (!item) + return -1; item->next = pevent->printklist; - item->printk = strdup(fmt); item->addr = addr; + item->printk = strdup(fmt); if (!item->printk) - die("malloc fmt"); + goto out_free; pevent->printklist = item; pevent->printk_count++; return 0; + +out_free: + free(item); + errno = ENOMEM; + return -1; } /** @@ -619,24 +648,18 @@ void pevent_print_printk(struct pevent *pevent) static struct event_format *alloc_event(void) { - struct event_format *event; - - event = malloc(sizeof(*event)); - if (!event) - return NULL; - memset(event, 0, sizeof(*event)); - - return event; + return calloc(1, sizeof(struct event_format)); } -static void add_event(struct pevent *pevent, struct event_format *event) +static int add_event(struct pevent *pevent, struct event_format *event) { int i; + struct event_format **events = realloc(pevent->events, sizeof(event) * + (pevent->nr_events + 1)); + if (!events) + return -1; - pevent->events = realloc(pevent->events, sizeof(event) * - (pevent->nr_events + 1)); - if (!pevent->events) - die("Can not allocate events"); + pevent->events = events; for (i = 0; i < pevent->nr_events; i++) { if (pevent->events[i]->id > event->id) @@ -651,6 +674,8 @@ static void add_event(struct pevent *pevent, struct event_format *event) pevent->nr_events++; event->pevent = pevent; + + return 0; } static int event_item_type(enum event_type type) @@ -827,9 +852,9 @@ static enum event_type __read_token(char **tok) switch (type) { case EVENT_NEWLINE: case EVENT_DELIM: - *tok = malloc_or_die(2); - (*tok)[0] = ch; - (*tok)[1] = 0; + if (asprintf(tok, "%c", ch) < 0) + return EVENT_ERROR; + return type; case EVENT_OP: @@ -1240,8 +1265,10 @@ static int event_read_fields(struct event_format *event, struct format_field **f last_token = token; - field = malloc_or_die(sizeof(*field)); - memset(field, 0, sizeof(*field)); + field = calloc(1, sizeof(*field)); + if (!field) + goto fail; + field->event = event; /* read the rest of the type */ @@ -1282,7 +1309,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f } if (!field->type) { - die("no type found"); + do_warning("%s: no type found", __func__); goto fail; } field->name = last_token; @@ -1329,7 +1356,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f free_token(token); type = read_token(&token); if (type == EVENT_NONE) { - die("failed to find token"); + do_warning("failed to find token"); goto fail; } } @@ -1538,6 +1565,14 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok) left = alloc_arg(); right = alloc_arg(); + if (!arg || !left || !right) { + do_warning("%s: not enough memory!", __func__); + /* arg will be freed at out_free */ + free_arg(left); + free_arg(right); + goto out_free; + } + arg->type = PRINT_OP; arg->op.left = left; arg->op.right = right; @@ -1580,6 +1615,12 @@ process_array(struct event_format *event, struct print_arg *top, char **tok) char *token = NULL; arg = alloc_arg(); + if (!arg) { + do_warning("%s: not enough memory!", __func__); + /* '*tok' is set to top->op.op. No need to free. */ + *tok = NULL; + return EVENT_ERROR; + } *tok = NULL; type = process_arg(event, arg, &token); @@ -1595,8 +1636,7 @@ process_array(struct event_format *event, struct print_arg *top, char **tok) return type; out_free: - free_token(*tok); - *tok = NULL; + free_token(token); free_arg(arg); return EVENT_ERROR; } @@ -1682,7 +1722,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) if (arg->type == PRINT_OP && !arg->op.left) { /* handle single op */ if (token[1]) { - die("bad op token %s", token); + do_warning("bad op token %s", token); goto out_free; } switch (token[0]) { @@ -1699,10 +1739,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) /* make an empty left */ left = alloc_arg(); + if (!left) + goto out_warn_free; + left->type = PRINT_NULL; arg->op.left = left; right = alloc_arg(); + if (!right) + goto out_warn_free; + arg->op.right = right; /* do not free the token, it belongs to an op */ @@ -1712,6 +1758,9 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) } else if (strcmp(token, "?") == 0) { left = alloc_arg(); + if (!left) + goto out_warn_free; + /* copy the top arg to the left */ *left = *arg; @@ -1720,6 +1769,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) arg->op.left = left; arg->op.prio = 0; + /* it will set arg->op.right */ type = process_cond(event, arg, tok); } else if (strcmp(token, ">>") == 0 || @@ -1739,6 +1789,8 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) strcmp(token, "!=") == 0) { left = alloc_arg(); + if (!left) + goto out_warn_free; /* copy the top arg to the left */ *left = *arg; @@ -1746,6 +1798,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) arg->type = PRINT_OP; arg->op.op = token; arg->op.left = left; + arg->op.right = NULL; if (set_op_prio(arg) == -1) { event->flags |= EVENT_FL_FAILED; @@ -1762,12 +1815,14 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) type == EVENT_DELIM && (strcmp(token, ")") == 0)) { char *new_atom; - if (left->type != PRINT_ATOM) - die("bad pointer type"); + if (left->type != PRINT_ATOM) { + do_warning("bad pointer type"); + goto out_free; + } new_atom = realloc(left->atom.atom, strlen(left->atom.atom) + 3); if (!new_atom) - goto out_free; + goto out_warn_free; left->atom.atom = new_atom; strcat(left->atom.atom, " *"); @@ -1779,12 +1834,18 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) } right = alloc_arg(); + if (!right) + goto out_warn_free; + type = process_arg_token(event, right, tok, type); arg->op.right = right; } else if (strcmp(token, "[") == 0) { left = alloc_arg(); + if (!left) + goto out_warn_free; + *left = *arg; arg->type = PRINT_OP; @@ -1793,6 +1854,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) arg->op.prio = 0; + /* it will set arg->op.right */ type = process_array(event, arg, tok); } else { @@ -1816,14 +1878,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) return type; - out_free: +out_warn_free: + do_warning("%s: not enough memory!", __func__); +out_free: free_token(token); *tok = NULL; return EVENT_ERROR; } static enum event_type -process_entry(struct event_format *event __unused, struct print_arg *arg, +process_entry(struct event_format *event __maybe_unused, struct print_arg *arg, char **tok) { enum event_type type; @@ -1880,7 +1944,11 @@ eval_type_str(unsigned long long val, const char *type, int pointer) return val; } - ref = malloc_or_die(len); + ref = malloc(len); + if (!ref) { + do_warning("%s: not enough memory!", __func__); + return val; + } memcpy(ref, type, len); /* chop off the " *" */ @@ -1957,8 +2025,10 @@ eval_type_str(unsigned long long val, const char *type, int pointer) static unsigned long long eval_type(unsigned long long val, struct print_arg *arg, int pointer) { - if (arg->type != PRINT_TYPE) - die("expected type argument"); + if (arg->type != PRINT_TYPE) { + do_warning("expected type argument"); + return 0; + } return eval_type_str(val, arg->typecast.type, pointer); } @@ -2143,7 +2213,7 @@ static char *arg_eval (struct print_arg *arg) case PRINT_STRING: case PRINT_BSTRING: default: - die("invalid eval type %d", arg->type); + do_warning("invalid eval type %d", arg->type); break; } @@ -2166,6 +2236,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** break; arg = alloc_arg(); + if (!arg) + goto out_free; free_token(token); type = process_arg(event, arg, &token); @@ -2179,30 +2251,33 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; - field = malloc_or_die(sizeof(*field)); - memset(field, 0, sizeof(*field)); + field = calloc(1, sizeof(*field)); + if (!field) + goto out_free; value = arg_eval(arg); if (value == NULL) - goto out_free; + goto out_free_field; field->value = strdup(value); if (field->value == NULL) - goto out_free; + goto out_free_field; free_arg(arg); arg = alloc_arg(); + if (!arg) + goto out_free; free_token(token); type = process_arg(event, arg, &token); if (test_type_token(type, token, EVENT_OP, "}")) - goto out_free; + goto out_free_field; value = arg_eval(arg); if (value == NULL) - goto out_free; + goto out_free_field; field->str = strdup(value); if (field->str == NULL) - goto out_free; + goto out_free_field; free_arg(arg); arg = NULL; @@ -2216,6 +2291,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** *tok = token; return type; +out_free_field: + free_flag_sym(field); out_free: free_arg(arg); free_token(token); @@ -2235,6 +2312,10 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok) arg->type = PRINT_FLAGS; field = alloc_arg(); + if (!field) { + do_warning("%s: not enough memory!", __func__); + goto out_free; + } type = process_arg(event, field, &token); @@ -2243,7 +2324,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok) type = process_op(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; + goto out_free_field; free_token(token); arg->flags.field = field; @@ -2265,7 +2346,9 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok) type = read_token_item(tok); return type; - out_free: +out_free_field: + free_arg(field); +out_free: free_token(token); *tok = NULL; return EVENT_ERROR; @@ -2282,10 +2365,14 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) arg->type = PRINT_SYMBOL; field = alloc_arg(); + if (!field) { + do_warning("%s: not enough memory!", __func__); + goto out_free; + } type = process_arg(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) - goto out_free; + goto out_free_field; arg->symbol.field = field; @@ -2297,7 +2384,9 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) type = read_token_item(tok); return type; - out_free: +out_free_field: + free_arg(field); +out_free: free_token(token); *tok = NULL; return EVENT_ERROR; @@ -2314,6 +2403,11 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok) arg->type = PRINT_HEX; field = alloc_arg(); + if (!field) { + do_warning("%s: not enough memory!", __func__); + goto out_free; + } + type = process_arg(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) @@ -2324,6 +2418,12 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok) free_token(token); field = alloc_arg(); + if (!field) { + do_warning("%s: not enough memory!", __func__); + *tok = NULL; + return EVENT_ERROR; + } + type = process_arg(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ")")) @@ -2381,6 +2481,12 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char ** free_token(token); arg = alloc_arg(); + if (!field) { + do_warning("%s: not enough memory!", __func__); + *tok = NULL; + return EVENT_ERROR; + } + type = process_arg(event, arg, &token); if (type == EVENT_ERROR) goto out_free_arg; @@ -2434,10 +2540,16 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok) /* make this a typecast and contine */ /* prevous must be an atom */ - if (arg->type != PRINT_ATOM) - die("previous needed to be PRINT_ATOM"); + if (arg->type != PRINT_ATOM) { + do_warning("previous needed to be PRINT_ATOM"); + goto out_free; + } item_arg = alloc_arg(); + if (!item_arg) { + do_warning("%s: not enough memory!", __func__); + goto out_free; + } arg->type = PRINT_TYPE; arg->typecast.type = arg->atom.atom; @@ -2457,7 +2569,8 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok) static enum event_type -process_str(struct event_format *event __unused, struct print_arg *arg, char **tok) +process_str(struct event_format *event __maybe_unused, struct print_arg *arg, + char **tok) { enum event_type type; char *token; @@ -2532,6 +2645,11 @@ process_func_handler(struct event_format *event, struct pevent_function_handler next_arg = &(arg->func.args); for (i = 0; i < func->nr_args; i++) { farg = alloc_arg(); + if (!farg) { + do_warning("%s: not enough memory!", __func__); + return EVENT_ERROR; + } + type = process_arg(event, farg, &token); if (i < (func->nr_args - 1)) test = ","; @@ -2676,7 +2794,8 @@ process_arg_token(struct event_format *event, struct print_arg *arg, case EVENT_ERROR ... EVENT_NEWLINE: default: - die("unexpected type %d", type); + do_warning("unexpected type %d", type); + return EVENT_ERROR; } *tok = token; @@ -2697,6 +2816,10 @@ static int event_read_print_args(struct event_format *event, struct print_arg ** } arg = alloc_arg(); + if (!arg) { + do_warning("%s: not enough memory!", __func__); + return -1; + } type = process_arg(event, arg, &token); @@ -2768,10 +2891,8 @@ static int event_read_print(struct event_format *event) if (type == EVENT_DQUOTE) { char *cat; - cat = malloc_or_die(strlen(event->print_fmt.format) + - strlen(token) + 1); - strcpy(cat, event->print_fmt.format); - strcat(cat, token); + if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0) + goto fail; free_token(token); free_token(event->print_fmt.format); event->print_fmt.format = NULL; @@ -2925,8 +3046,10 @@ static int get_common_info(struct pevent *pevent, * All events should have the same common elements. * Pick any event to find where the type is; */ - if (!pevent->events) - die("no event_list!"); + if (!pevent->events) { + do_warning("no event_list!"); + return -1; + } event = pevent->events[0]; field = pevent_find_common_field(event, type); @@ -3084,7 +3207,8 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg if (!arg->field.field) { arg->field.field = pevent_find_any_field(event, arg->field.name); if (!arg->field.field) - die("field %s not found", arg->field.name); + goto out_warning_field; + } /* must be a number */ val = pevent_read_number(pevent, data + arg->field.field->offset, @@ -3145,8 +3269,10 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg if (!larg->field.field) { larg->field.field = pevent_find_any_field(event, larg->field.name); - if (!larg->field.field) - die("field %s not found", larg->field.name); + if (!larg->field.field) { + arg = larg; + goto out_warning_field; + } } field_size = larg->field.field->elementsize; offset = larg->field.field->offset + @@ -3182,7 +3308,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg val = left != right; break; default: - die("unknown op '%s'", arg->op.op); + goto out_warning_op; } break; case '~': @@ -3212,7 +3338,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg val = left <= right; break; default: - die("unknown op '%s'", arg->op.op); + goto out_warning_op; } break; case '>': @@ -3227,12 +3353,13 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg val = left >= right; break; default: - die("unknown op '%s'", arg->op.op); + goto out_warning_op; } break; case '=': if (arg->op.op[1] != '=') - die("unknown op '%s'", arg->op.op); + goto out_warning_op; + val = left == right; break; case '-': @@ -3248,13 +3375,21 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg val = left * right; break; default: - die("unknown op '%s'", arg->op.op); + goto out_warning_op; } break; default: /* not sure what to do there */ return 0; } return val; + +out_warning_op: + do_warning("%s: unknown op '%s'", __func__, arg->op.op); + return 0; + +out_warning_field: + do_warning("%s: field %s not found", __func__, arg->field.name); + return 0; } struct flag { @@ -3331,8 +3466,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, field = arg->field.field; if (!field) { field = pevent_find_any_field(event, arg->field.name); - if (!field) - die("field %s not found", arg->field.name); + if (!field) { + str = arg->field.name; + goto out_warning_field; + } arg->field.field = field; } /* Zero sized fields, mean the rest of the data */ @@ -3349,7 +3486,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, trace_seq_printf(s, "%lx", addr); break; } - str = malloc_or_die(len + 1); + str = malloc(len + 1); + if (!str) { + do_warning("%s: not enough memory!", __func__); + return; + } memcpy(str, data + field->offset, len); str[len] = 0; print_str_to_seq(s, format, len_arg, str); @@ -3389,7 +3530,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, str = arg->hex.field->field.name; field = pevent_find_any_field(event, str); if (!field) - die("field %s not found", str); + goto out_warning_field; arg->hex.field->field.field = field; } hex = data + field->offset; @@ -3441,6 +3582,11 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, /* well... */ break; } + + return; + +out_warning_field: + do_warning("%s: field %s not found", __func__, arg->field.name); } static unsigned long long @@ -3467,7 +3613,11 @@ process_defined_func(struct trace_seq *s, void *data, int size, farg = arg->func.args; param = func_handle->params; - args = malloc_or_die(sizeof(*args) * func_handle->nr_args); + ret = ULLONG_MAX; + args = malloc(sizeof(*args) * func_handle->nr_args); + if (!args) + goto out; + for (i = 0; i < func_handle->nr_args; i++) { switch (param->type) { case PEVENT_FUNC_ARG_INT: @@ -3479,13 +3629,19 @@ process_defined_func(struct trace_seq *s, void *data, int size, trace_seq_init(&str); print_str_arg(&str, data, size, event, "%s", -1, farg); trace_seq_terminate(&str); - string = malloc_or_die(sizeof(*string)); + string = malloc(sizeof(*string)); + if (!string) { + do_warning("%s(%d): malloc str", __func__, __LINE__); + goto out_free; + } string->next = strings; string->str = strdup(str.buffer); - if (!string->str) - die("malloc str"); - - args[i] = (unsigned long long)string->str; + if (!string->str) { + free(string); + do_warning("%s(%d): malloc str", __func__, __LINE__); + goto out_free; + } + args[i] = (uintptr_t)string->str; strings = string; trace_seq_destroy(&str); break; @@ -3494,14 +3650,15 @@ process_defined_func(struct trace_seq *s, void *data, int size, * Something went totally wrong, this is not * an input error, something in this code broke. */ - die("Unexpected end of arguments\n"); - break; + do_warning("Unexpected end of arguments\n"); + goto out_free; } farg = farg->next; param = param->next; } ret = (*func_handle->func)(s, args); +out_free: free(args); while (strings) { string = strings; @@ -3515,6 +3672,18 @@ process_defined_func(struct trace_seq *s, void *data, int size, return ret; } +static void free_args(struct print_arg *args) +{ + struct print_arg *next; + + while (args) { + next = args->next; + + free_arg(args); + args = next; + } +} + static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event_format *event) { struct pevent *pevent = event->pevent; @@ -3530,11 +3699,15 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc if (!field) { field = pevent_find_field(event, "buf"); - if (!field) - die("can't find buffer field for binary printk"); + if (!field) { + do_warning("can't find buffer field for binary printk"); + return NULL; + } ip_field = pevent_find_field(event, "ip"); - if (!ip_field) - die("can't find ip field for binary printk"); + if (!ip_field) { + do_warning("can't find ip field for binary printk"); + return NULL; + } pevent->bprint_buf_field = field; pevent->bprint_ip_field = ip_field; } @@ -3545,13 +3718,18 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc * The first arg is the IP pointer. */ args = alloc_arg(); + if (!args) { + do_warning("%s(%d): not enough memory!", __func__, __LINE__); + return NULL; + } arg = args; arg->next = NULL; next = &arg->next; arg->type = PRINT_ATOM; - arg->atom.atom = malloc_or_die(32); - sprintf(arg->atom.atom, "%lld", ip); + + if (asprintf(&arg->atom.atom, "%lld", ip) < 0) + goto out_free; /* skip the first "%pf : " */ for (ptr = fmt + 6, bptr = data + field->offset; @@ -3606,10 +3784,17 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc val = pevent_read_number(pevent, bptr, vsize); bptr += vsize; arg = alloc_arg(); + if (!arg) { + do_warning("%s(%d): not enough memory!", + __func__, __LINE__); + goto out_free; + } arg->next = NULL; arg->type = PRINT_ATOM; - arg->atom.atom = malloc_or_die(32); - sprintf(arg->atom.atom, "%lld", val); + if (asprintf(&arg->atom.atom, "%lld", val) < 0) { + free(arg); + goto out_free; + } *next = arg; next = &arg->next; /* @@ -3622,11 +3807,16 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc break; case 's': arg = alloc_arg(); + if (!arg) { + do_warning("%s(%d): not enough memory!", + __func__, __LINE__); + goto out_free; + } arg->next = NULL; arg->type = PRINT_BSTRING; arg->string.string = strdup(bptr); if (!arg->string.string) - break; + goto out_free; bptr += strlen(bptr) + 1; *next = arg; next = &arg->next; @@ -3637,22 +3827,15 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc } return args; -} -static void free_args(struct print_arg *args) -{ - struct print_arg *next; - - while (args) { - next = args->next; - - free_arg(args); - args = next; - } +out_free: + free_args(args); + return NULL; } static char * -get_bprint_format(void *data, int size __unused, struct event_format *event) +get_bprint_format(void *data, int size __maybe_unused, + struct event_format *event) { struct pevent *pevent = event->pevent; unsigned long long addr; @@ -3665,8 +3848,10 @@ get_bprint_format(void *data, int size __unused, struct event_format *event) if (!field) { field = pevent_find_field(event, "fmt"); - if (!field) - die("can't find format field for binary printk"); + if (!field) { + do_warning("can't find format field for binary printk"); + return NULL; + } pevent->bprint_fmt_field = field; } @@ -3674,9 +3859,8 @@ get_bprint_format(void *data, int size __unused, struct event_format *event) printk = find_printk(pevent, addr); if (!printk) { - format = malloc_or_die(45); - sprintf(format, "%%pf : (NO FORMAT FOUND at %llx)\n", - addr); + if (asprintf(&format, "%%pf : (NO FORMAT FOUND at %llx)\n", addr) < 0) + return NULL; return format; } @@ -3684,8 +3868,8 @@ get_bprint_format(void *data, int size __unused, struct event_format *event) /* Remove any quotes. */ if (*p == '"') p++; - format = malloc_or_die(strlen(p) + 10); - sprintf(format, "%s : %s", "%pf", p); + if (asprintf(&format, "%s : %s", "%pf", p) < 0) + return NULL; /* remove ending quotes and new line since we will add one too */ p = format + strlen(format) - 1; if (*p == '"') @@ -3720,8 +3904,11 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size, if (!arg->field.field) { arg->field.field = pevent_find_any_field(event, arg->field.name); - if (!arg->field.field) - die("field %s not found", arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return; + } } if (arg->field.field->size != 6) { trace_seq_printf(s, "INVALIDMAC"); @@ -3888,8 +4075,11 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event goto cont_process; case '*': /* The argument is the length. */ - if (!arg) - die("no argument match"); + if (!arg) { + do_warning("no argument match"); + event->flags |= EVENT_FL_FAILED; + goto out_failed; + } len_arg = eval_num_arg(data, size, event, arg); len_as_arg = 1; arg = arg->next; @@ -3922,15 +4112,21 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event case 'x': case 'X': case 'u': - if (!arg) - die("no argument match"); + if (!arg) { + do_warning("no argument match"); + event->flags |= EVENT_FL_FAILED; + goto out_failed; + } len = ((unsigned long)ptr + 1) - (unsigned long)saveptr; /* should never happen */ - if (len > 31) - die("bad format!"); + if (len > 31) { + do_warning("bad format!"); + event->flags |= EVENT_FL_FAILED; + len = 31; + } memcpy(format, saveptr, len); format[len] = 0; @@ -3994,19 +4190,26 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event trace_seq_printf(s, format, (long long)val); break; default: - die("bad count (%d)", ls); + do_warning("bad count (%d)", ls); + event->flags |= EVENT_FL_FAILED; } break; case 's': - if (!arg) - die("no matching argument"); + if (!arg) { + do_warning("no matching argument"); + event->flags |= EVENT_FL_FAILED; + goto out_failed; + } len = ((unsigned long)ptr + 1) - (unsigned long)saveptr; /* should never happen */ - if (len > 31) - die("bad format!"); + if (len > 31) { + do_warning("bad format!"); + event->flags |= EVENT_FL_FAILED; + len = 31; + } memcpy(format, saveptr, len); format[len] = 0; @@ -4024,6 +4227,11 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event trace_seq_putc(s, *ptr); } + if (event->flags & EVENT_FL_FAILED) { +out_failed: + trace_seq_printf(s, "[FAILED TO PARSE]"); + } + if (args) { free_args(args); free(bprint_fmt); @@ -4356,7 +4564,10 @@ get_event_fields(const char *type, const char *name, struct format_field *field; int i = 0; - fields = malloc_or_die(sizeof(*fields) * (count + 1)); + fields = malloc(sizeof(*fields) * (count + 1)); + if (!fields) + return NULL; + for (field = list; field; field = field->next) { fields[i++] = field; if (i == count + 1) { @@ -4672,8 +4883,7 @@ static int find_event_handle(struct pevent *pevent, struct event_format *event) } /** - * pevent_parse_event - parse the event format - * @pevent: the handle to the pevent + * __pevent_parse_format - parse the event format * @buf: the buffer storing the event format string * @size: the size of @buf * @sys: the system the event belongs to @@ -4685,28 +4895,27 @@ static int find_event_handle(struct pevent *pevent, struct event_format *event) * * /sys/kernel/debug/tracing/events/.../.../format */ -int pevent_parse_event(struct pevent *pevent, - const char *buf, unsigned long size, - const char *sys) +enum pevent_errno __pevent_parse_format(struct event_format **eventp, + struct pevent *pevent, const char *buf, + unsigned long size, const char *sys) { struct event_format *event; int ret; init_input_buf(buf, size); - event = alloc_event(); + *eventp = event = alloc_event(); if (!event) - return -ENOMEM; + return PEVENT_ERRNO__MEM_ALLOC_FAILED; event->name = event_read_name(); if (!event->name) { /* Bad event? */ - free(event); - return -1; + ret = PEVENT_ERRNO__MEM_ALLOC_FAILED; + goto event_alloc_failed; } if (strcmp(sys, "ftrace") == 0) { - event->flags |= EVENT_FL_ISFTRACE; if (strcmp(event->name, "bprint") == 0) @@ -4714,74 +4923,189 @@ int pevent_parse_event(struct pevent *pevent, } event->id = event_read_id(); - if (event->id < 0) - die("failed to read event id"); + if (event->id < 0) { + ret = PEVENT_ERRNO__READ_ID_FAILED; + /* + * This isn't an allocation error actually. + * But as the ID is critical, just bail out. + */ + goto event_alloc_failed; + } event->system = strdup(sys); - if (!event->system) - die("failed to allocate system"); - - /* Add pevent to event so that it can be referenced */ - event->pevent = pevent; + if (!event->system) { + ret = PEVENT_ERRNO__MEM_ALLOC_FAILED; + goto event_alloc_failed; + } ret = event_read_format(event); if (ret < 0) { - do_warning("failed to read event format for %s", event->name); - goto event_failed; + ret = PEVENT_ERRNO__READ_FORMAT_FAILED; + goto event_parse_failed; } /* * If the event has an override, don't print warnings if the event * print format fails to parse. */ - if (find_event_handle(pevent, event)) + if (pevent && find_event_handle(pevent, event)) show_warning = 0; ret = event_read_print(event); - if (ret < 0) { - do_warning("failed to read event print fmt for %s", - event->name); - show_warning = 1; - goto event_failed; - } show_warning = 1; - add_event(pevent, event); + if (ret < 0) { + ret = PEVENT_ERRNO__READ_PRINT_FAILED; + goto event_parse_failed; + } if (!ret && (event->flags & EVENT_FL_ISFTRACE)) { struct format_field *field; struct print_arg *arg, **list; /* old ftrace had no args */ - list = &event->print_fmt.args; for (field = event->format.fields; field; field = field->next) { arg = alloc_arg(); - *list = arg; - list = &arg->next; + if (!arg) { + event->flags |= EVENT_FL_FAILED; + return PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED; + } arg->type = PRINT_FIELD; arg->field.name = strdup(field->name); if (!arg->field.name) { - do_warning("failed to allocate field name"); event->flags |= EVENT_FL_FAILED; - return -1; + free_arg(arg); + return PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED; } arg->field.field = field; + *list = arg; + list = &arg->next; } return 0; } + return 0; + + event_parse_failed: + event->flags |= EVENT_FL_FAILED; + return ret; + + event_alloc_failed: + free(event->system); + free(event->name); + free(event); + *eventp = NULL; + return ret; +} + +/** + * pevent_parse_format - parse the event format + * @buf: the buffer storing the event format string + * @size: the size of @buf + * @sys: the system the event belongs to + * + * This parses the event format and creates an event structure + * to quickly parse raw data for a given event. + * + * These files currently come from: + * + * /sys/kernel/debug/tracing/events/.../.../format + */ +enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf, + unsigned long size, const char *sys) +{ + return __pevent_parse_format(eventp, NULL, buf, size, sys); +} + +/** + * pevent_parse_event - parse the event format + * @pevent: the handle to the pevent + * @buf: the buffer storing the event format string + * @size: the size of @buf + * @sys: the system the event belongs to + * + * This parses the event format and creates an event structure + * to quickly parse raw data for a given event. + * + * These files currently come from: + * + * /sys/kernel/debug/tracing/events/.../.../format + */ +enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf, + unsigned long size, const char *sys) +{ + struct event_format *event = NULL; + int ret = __pevent_parse_format(&event, pevent, buf, size, sys); + + if (event == NULL) + return ret; + + /* Add pevent to event so that it can be referenced */ + event->pevent = pevent; + + if (add_event(pevent, event)) { + ret = PEVENT_ERRNO__MEM_ALLOC_FAILED; + goto event_add_failed; + } + #define PRINT_ARGS 0 if (PRINT_ARGS && event->print_fmt.args) print_args(event->print_fmt.args); return 0; - event_failed: - event->flags |= EVENT_FL_FAILED; - /* still add it even if it failed */ - add_event(pevent, event); - return -1; +event_add_failed: + pevent_free_format(event); + return ret; +} + +#undef _PE +#define _PE(code, str) str +static const char * const pevent_error_str[] = { + PEVENT_ERRORS +}; +#undef _PE + +int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum, + char *buf, size_t buflen) +{ + int idx; + const char *msg; + + if (errnum >= 0) { + msg = strerror_r(errnum, buf, buflen); + if (msg != buf) { + size_t len = strlen(msg); + memcpy(buf, msg, min(buflen - 1, len)); + *(buf + min(buflen - 1, len)) = '\0'; + } + return 0; + } + + if (errnum <= __PEVENT_ERRNO__START || + errnum >= __PEVENT_ERRNO__END) + return -1; + + idx = errnum - __PEVENT_ERRNO__START - 1; + msg = pevent_error_str[idx]; + + switch (errnum) { + case PEVENT_ERRNO__MEM_ALLOC_FAILED: + case PEVENT_ERRNO__PARSE_EVENT_FAILED: + case PEVENT_ERRNO__READ_ID_FAILED: + case PEVENT_ERRNO__READ_FORMAT_FAILED: + case PEVENT_ERRNO__READ_PRINT_FAILED: + case PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED: + snprintf(buf, buflen, "%s", msg); + break; + + default: + /* cannot reach here */ + break; + } + + return 0; } int get_field_val(struct trace_seq *s, struct format_field *field, @@ -5000,6 +5324,7 @@ int pevent_register_print_function(struct pevent *pevent, struct pevent_func_params *param; enum pevent_func_arg_type type; va_list ap; + int ret; func_handle = find_func_handler(pevent, name); if (func_handle) { @@ -5012,14 +5337,20 @@ int pevent_register_print_function(struct pevent *pevent, remove_func_handler(pevent, name); } - func_handle = malloc_or_die(sizeof(*func_handle)); - memset(func_handle, 0, sizeof(*func_handle)); + func_handle = calloc(1, sizeof(*func_handle)); + if (!func_handle) { + do_warning("Failed to allocate function handler"); + return PEVENT_ERRNO__MEM_ALLOC_FAILED; + } func_handle->ret_type = ret_type; func_handle->name = strdup(name); func_handle->func = func; - if (!func_handle->name) - die("Failed to allocate function name"); + if (!func_handle->name) { + do_warning("Failed to allocate function name"); + free(func_handle); + return PEVENT_ERRNO__MEM_ALLOC_FAILED; + } next_param = &(func_handle->params); va_start(ap, name); @@ -5029,11 +5360,17 @@ int pevent_register_print_function(struct pevent *pevent, break; if (type < 0 || type >= PEVENT_FUNC_ARG_MAX_TYPES) { - warning("Invalid argument type %d", type); + do_warning("Invalid argument type %d", type); + ret = PEVENT_ERRNO__INVALID_ARG_TYPE; goto out_free; } - param = malloc_or_die(sizeof(*param)); + param = malloc(sizeof(*param)); + if (!param) { + do_warning("Failed to allocate function param"); + ret = PEVENT_ERRNO__MEM_ALLOC_FAILED; + goto out_free; + } param->type = type; param->next = NULL; @@ -5051,7 +5388,7 @@ int pevent_register_print_function(struct pevent *pevent, out_free: va_end(ap); free_func_handle(func_handle); - return -1; + return ret; } /** @@ -5103,8 +5440,12 @@ int pevent_register_event_handler(struct pevent *pevent, not_found: /* Save for later use. */ - handle = malloc_or_die(sizeof(*handle)); - memset(handle, 0, sizeof(*handle)); + handle = calloc(1, sizeof(*handle)); + if (!handle) { + do_warning("Failed to allocate event handler"); + return PEVENT_ERRNO__MEM_ALLOC_FAILED; + } + handle->id = id; if (event_name) handle->event_name = strdup(event_name); @@ -5113,7 +5454,11 @@ int pevent_register_event_handler(struct pevent *pevent, if ((event_name && !handle->event_name) || (sys_name && !handle->sys_name)) { - die("Failed to allocate event/sys name"); + do_warning("Failed to allocate event/sys name"); + free((void *)handle->event_name); + free((void *)handle->sys_name); + free(handle); + return PEVENT_ERRNO__MEM_ALLOC_FAILED; } handle->func = func; @@ -5129,13 +5474,10 @@ int pevent_register_event_handler(struct pevent *pevent, */ struct pevent *pevent_alloc(void) { - struct pevent *pevent; + struct pevent *pevent = calloc(1, sizeof(*pevent)); - pevent = malloc(sizeof(*pevent)); - if (!pevent) - return NULL; - memset(pevent, 0, sizeof(*pevent)); - pevent->ref_count = 1; + if (pevent) + pevent->ref_count = 1; return pevent; } @@ -5164,7 +5506,7 @@ static void free_formats(struct format *format) free_format_fields(format->fields); } -static void free_event(struct event_format *event) +void pevent_free_format(struct event_format *event) { free(event->name); free(event->system); @@ -5250,7 +5592,7 @@ void pevent_free(struct pevent *pevent) } for (i = 0; i < pevent->nr_events; i++) - free_event(pevent->events[i]); + pevent_free_format(pevent->events[i]); while (pevent->handlers) { handle = pevent->handlers; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 5772ad8cb386..24a4bbabc5d5 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -24,8 +24,8 @@ #include <stdarg.h> #include <regex.h> -#ifndef __unused -#define __unused __attribute__ ((unused)) +#ifndef __maybe_unused +#define __maybe_unused __attribute__((unused)) #endif /* ----------------------- trace_seq ----------------------- */ @@ -49,7 +49,7 @@ struct pevent_record { int cpu; int ref_count; int locked; /* Do not free, even if ref_count is zero */ - void *private; + void *priv; #if DEBUG_RECORD struct pevent_record *prev; struct pevent_record *next; @@ -106,7 +106,7 @@ struct plugin_option { char *plugin_alias; char *description; char *value; - void *private; + void *priv; int set; }; @@ -345,6 +345,35 @@ enum pevent_flag { PEVENT_NSEC_OUTPUT = 1, /* output in NSECS */ }; +#define PEVENT_ERRORS \ + _PE(MEM_ALLOC_FAILED, "failed to allocate memory"), \ + _PE(PARSE_EVENT_FAILED, "failed to parse event"), \ + _PE(READ_ID_FAILED, "failed to read event id"), \ + _PE(READ_FORMAT_FAILED, "failed to read event format"), \ + _PE(READ_PRINT_FAILED, "failed to read event print fmt"), \ + _PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\ + _PE(INVALID_ARG_TYPE, "invalid argument type") + +#undef _PE +#define _PE(__code, __str) PEVENT_ERRNO__ ## __code +enum pevent_errno { + PEVENT_ERRNO__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __PEVENT_ERRNO__START = -100000, + + PEVENT_ERRORS, + + __PEVENT_ERRNO__END, +}; +#undef _PE + struct cmdline; struct cmdline_list; struct func_map; @@ -509,8 +538,11 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s, int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long size, int long_size); -int pevent_parse_event(struct pevent *pevent, const char *buf, - unsigned long size, const char *sys); +enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf, + unsigned long size, const char *sys); +enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf, + unsigned long size, const char *sys); +void pevent_free_format(struct event_format *event); void *pevent_get_field_raw(struct trace_seq *s, struct event_format *event, const char *name, struct pevent_record *record, @@ -561,6 +593,8 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec); const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid); void pevent_event_info(struct trace_seq *s, struct event_format *event, struct pevent_record *record); +int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum, + char *buf, size_t buflen); struct event_format **pevent_list_events(struct pevent *pevent, enum event_sort_type); struct format_field **pevent_event_common_fields(struct event_format *event); diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h index 08296383d1e6..bc075006966e 100644 --- a/tools/lib/traceevent/event-utils.h +++ b/tools/lib/traceevent/event-utils.h @@ -39,6 +39,12 @@ void __vdie(const char *fmt, ...); void __vwarning(const char *fmt, ...); void __vpr_stat(const char *fmt, ...); +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) + static inline char *strim(char *string) { char *ret; diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 26b823b61aa1..8f8fbc227a46 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -21,3 +21,5 @@ config.mak config.mak.autogen *-bison.* *-flex.* +*.pyc +*.pyo diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index ca600e09c8d4..9f2e44f2b17a 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -195,10 +195,10 @@ install-pdf: pdf #install-html: html # '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) -../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE - $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE +$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE + $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE --include ../PERF-VERSION-FILE +-include $(OUTPUT)PERF-VERSION-FILE # # Determine "include::" file references in asciidoc files. diff --git a/tools/perf/Documentation/jit-interface.txt b/tools/perf/Documentation/jit-interface.txt new file mode 100644 index 000000000000..a8656f564915 --- /dev/null +++ b/tools/perf/Documentation/jit-interface.txt @@ -0,0 +1,15 @@ +perf supports a simple JIT interface to resolve symbols for dynamic code generated +by a JIT. + +The JIT has to write a /tmp/perf-%d.map (%d = pid of process) file + +This is a text file. + +Each line has the following format, fields separated with spaces: + +START SIZE symbolname + +START and SIZE are hex numbers without 0x. +symbolname is the rest of the line, so it could contain special characters. + +The ownership of the file has to match the process. diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index c89f9e1453f7..c8ffd9fd5c6a 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -85,6 +85,9 @@ OPTIONS -M:: --disassembler-style=:: Set disassembler style for objdump. +--objdump=<path>:: + Path to objdump binary. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 74d7481ed7a6..ab7f667de1b1 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -17,6 +17,9 @@ captured via perf record. If no parameters are passed it will assume perf.data.old and perf.data. +The differential profile is displayed only for events matching both +specified perf.data files. + OPTIONS ------- -M:: diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index dd84cb2f0a88..326f2cb333cb 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -12,7 +12,7 @@ SYNOPSIS [--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]] {top|record|report|diff|buildid-list} 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path> - | --guestvmlinux=<path>] {top|record|report|diff|buildid-list} + | --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} DESCRIPTION ----------- @@ -38,6 +38,18 @@ There are a couple of variants of perf kvm: so that other tools can be used to fetch packages with matching symbol tables for use by perf report. + 'perf kvm stat <command>' to run a command and gather performance counter + statistics. + Especially, perf 'kvm stat record/report' generates a statistical analysis + of KVM events. Currently, vmexit, mmio and ioport events are supported. + 'perf kvm stat record <command>' records kvm events and the events between + start and end <command>. + And this command produces a file which contains tracing results of kvm + events. + + 'perf kvm stat report' reports statistical data which includes events + handled time, samples, and so on. + OPTIONS ------- -i:: @@ -68,7 +80,21 @@ OPTIONS --guestvmlinux=<path>:: Guest os kernel vmlinux. +STAT REPORT OPTIONS +------------------- +--vcpu=<value>:: + analyze events which occures on this vcpu. (default: all vcpus) + +--events=<value>:: + events to be analyzed. Possible values: vmexit, mmio, ioport. + (default: vmexit) +-k:: +--key=<value>:: + Sorting key. Possible values: sample (default, sort by samples + number), time (sort by average time). + SEE ALSO -------- linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1], -linkperf:perf-diff[1], linkperf:perf-buildid-list[1] +linkperf:perf-diff[1], linkperf:perf-buildid-list[1], +linkperf:perf-stat[1] diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index ddc22525228d..d1e39dc8c810 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -15,24 +15,43 @@ DESCRIPTION This command displays the symbolic event types which can be selected in the various perf commands with the -e option. +[[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- Events can optionally have a modifer by appending a colon and one or -more modifiers. Modifiers allow the user to restrict when events are -counted with 'u' for user-space, 'k' for kernel, 'h' for hypervisor. -Additional modifiers are 'G' for guest counting (in KVM guests) and 'H' -for host counting (not in KVM guests). +more modifiers. Modifiers allow the user to restrict the events to be +counted. The following modifiers exist: + + u - user-space counting + k - kernel counting + h - hypervisor counting + G - guest counting (in KVM guests) + H - host counting (not in KVM guests) + p - precise level The 'p' modifier can be used for specifying how precise the instruction -address should be. The 'p' modifier is currently only implemented for -Intel PEBS and can be specified multiple times: - 0 - SAMPLE_IP can have arbitrary skid - 1 - SAMPLE_IP must have constant skid - 2 - SAMPLE_IP requested to have 0 skid - 3 - SAMPLE_IP must have 0 skid +address should be. The 'p' modifier can be specified multiple times: + + 0 - SAMPLE_IP can have arbitrary skid + 1 - SAMPLE_IP must have constant skid + 2 - SAMPLE_IP requested to have 0 skid + 3 - SAMPLE_IP must have 0 skid + +For Intel systems precise event sampling is implemented with PEBS +which supports up to precise-level 2. -The PEBS implementation now supports up to 2. +On AMD systems it is implemented using IBS (up to precise-level 2). +The precise modifier works with event types 0x76 (cpu-cycles, CPU +clocks not halted) and 0xC1 (micro-ops retired). Both events map to +IBS execution sampling (IBS op) with the IBS Op Counter Control bit +(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s +Manual Volume 2: System Programming, 13.3 Instruction-Based +Sampling). Examples to use IBS: + + perf record -a -e cpu-cycles:p ... # use ibs op counting cycles + perf record -a -e r076:p ... # same as -e cpu-cycles:p + perf record -a -e r0C1:p ... # use ibs op counting micro-ops RAW HARDWARE EVENT DESCRIPTOR ----------------------------- @@ -44,6 +63,11 @@ layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Softwar of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344, Figure 13-7 Performance Event-Select Register (PerfEvtSeln)). +Note: Only the following bit fields can be set in x86 counter +registers: event, umask, edge, inv, cmask. Esp. guest/host only and +OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT +MODIFIERS>>. + Example: If the Intel docs for a QM720 Core i7 describe an event as: @@ -91,4 +115,4 @@ SEE ALSO linkperf:perf-stat[1], linkperf:perf-top[1], linkperf:perf-record[1], http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], -http://support.amd.com/us/Processor_TechDocs/24593.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] +http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 495210a612c4..f4d91bebd59d 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -168,6 +168,9 @@ OPTIONS branch stacks and it will automatically switch to the branch view mode, unless --no-branch-stack is used. +--objdump=<path>:: + Path to objdump binary. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1] diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 3152cca15501..d00bef231340 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -116,8 +116,8 @@ search path and 'use'ing a few support modules (see module descriptions below): ---- - use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/perf-script-Util/lib"; - use lib "./perf-script-Util/lib"; + use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; + use lib "./Perf-Trace-Util/lib"; use Perf::Trace::Core; use Perf::Trace::Context; use Perf::Trace::Util; diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 471022069119..a4027f221a53 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -129,7 +129,7 @@ import os import sys sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/perf-script-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from perf_trace_context import * from Core import * @@ -216,7 +216,7 @@ import os import sys sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/perf-script-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from perf_trace_context import * from Core import * @@ -279,7 +279,7 @@ import os import sys sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/perf-script-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from perf_trace_context import * from Core import * @@ -391,7 +391,7 @@ drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 . drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 .. drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin -rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py -drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 perf-script-Util +drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util -rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py ---- @@ -518,7 +518,7 @@ descriptions below): import sys sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/perf-script-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from perf_trace_context import * from Core import * diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt new file mode 100644 index 000000000000..3a2ae37310a9 --- /dev/null +++ b/tools/perf/Documentation/perf-trace.txt @@ -0,0 +1,53 @@ +perf-trace(1) +============= + +NAME +---- +perf-trace - strace inspired tool + +SYNOPSIS +-------- +[verse] +'perf trace' + +DESCRIPTION +----------- +This command will show the events associated with the target, initially +syscalls, but other system events like pagefaults, task lifetime events, +scheduling events, etc. + +Initially this is a live mode only tool, but eventually will work with +perf.data files like the other tools, allowing a detached 'record' from +analysis phases. + +OPTIONS +------- + +--all-cpus:: + System-wide collection from all CPUs. + +-p:: +--pid=:: + Record events on existing process ID (comma separated list). + +--tid=:: + Record events on existing thread ID (comma separated list). + +--uid=:: + Record events in threads owned by uid. Name or number. + +--no-inherit:: + Child tasks do not inherit counters. + +--mmap-pages=:: + Number of mmap data pages. Must be a power of two. + +--cpu:: +Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a +comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. +In per-thread mode with inheritance mode on (default), Events are captured only when +the thread executes on the designated CPUs. Default is to monitor all CPUs. + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index b4b572e8c100..80db3f4bcf7a 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -10,8 +10,12 @@ include/linux/stringify.h lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h +arch/*/include/asm/perf_regs.h arch/*/lib/memcpy*.S arch/*/lib/memset*.S include/linux/poison.h include/linux/magic.h include/linux/hw_breakpoint.h +arch/x86/include/asm/svm.h +arch/x86/include/asm/vmx.h +arch/x86/include/asm/kvm_host.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 35655c3a7b7a..e5e71e7d95a0 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -37,7 +37,14 @@ include config/utilities.mak # # Define NO_NEWT if you do not want TUI support. # +# Define NO_GTK2 if you do not want GTK+ GUI support. +# # Define NO_DEMANGLE if you do not want C++ symbol demangling. +# +# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds) +# +# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf +# backtrace post unwind. $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) @@ -50,16 +57,19 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ ) +NO_PERF_REGS := 1 CC = $(CROSS_COMPILE)gcc AR = $(CROSS_COMPILE)ar # Additional ARCH settings for x86 ifeq ($(ARCH),i386) - ARCH := x86 + override ARCH := x86 + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-x86 endif ifeq ($(ARCH),x86_64) - ARCH := x86 + override ARCH := x86 IS_X86_64 := 0 ifeq (, $(findstring m32,$(EXTRA_CFLAGS))) IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1) @@ -69,6 +79,8 @@ ifeq ($(ARCH),x86_64) ARCH_CFLAGS := -DARCH_X86_64 ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S endif + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 endif # Treat warnings as errors unless directed not to @@ -89,7 +101,7 @@ ifdef PARSER_DEBUG PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG endif -CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS) +CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS) EXTLIBS = -lpthread -lrt -lelf -lm ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE ALL_LDFLAGS = $(LDFLAGS) @@ -186,10 +198,10 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) TRACE_EVENT_DIR = ../lib/traceevent/ -ifeq ("$(origin O)", "command line") - TE_PATH=$(OUTPUT)/ +ifneq ($(OUTPUT),) + TE_PATH=$(OUTPUT) else - TE_PATH=$(TRACE_EVENT_DIR)/ + TE_PATH=$(TRACE_EVENT_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a @@ -221,13 +233,13 @@ export PERL_PATH FLEX = flex BISON= bison -$(OUTPUT)util/parse-events-flex.c: util/parse-events.l +$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c: util/parse-events.y $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -$(OUTPUT)util/pmu-flex.c: util/pmu.l +$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c: util/pmu.y @@ -252,6 +264,7 @@ LIB_H += util/include/linux/ctype.h LIB_H += util/include/linux/kernel.h LIB_H += util/include/linux/list.h LIB_H += util/include/linux/export.h +LIB_H += util/include/linux/magic.h LIB_H += util/include/linux/poison.h LIB_H += util/include/linux/prefetch.h LIB_H += util/include/linux/rbtree.h @@ -321,6 +334,10 @@ LIB_H += $(TRACE_EVENT_DIR)event-parse.h LIB_H += util/target.h LIB_H += util/rblist.h LIB_H += util/intlist.h +LIB_H += util/perf_regs.h +LIB_H += util/unwind.h +LIB_H += ui/helpline.h +LIB_H += util/vdso.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -356,6 +373,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o LIB_OBJS += $(OUTPUT)util/wrapper.o LIB_OBJS += $(OUTPUT)util/sigchain.o LIB_OBJS += $(OUTPUT)util/symbol.o +LIB_OBJS += $(OUTPUT)util/symbol-elf.o LIB_OBJS += $(OUTPUT)util/dso-test-data.o LIB_OBJS += $(OUTPUT)util/color.o LIB_OBJS += $(OUTPUT)util/pager.o @@ -387,11 +405,15 @@ LIB_OBJS += $(OUTPUT)util/cgroup.o LIB_OBJS += $(OUTPUT)util/target.o LIB_OBJS += $(OUTPUT)util/rblist.o LIB_OBJS += $(OUTPUT)util/intlist.o +LIB_OBJS += $(OUTPUT)util/vdso.o +LIB_OBJS += $(OUTPUT)util/stat.o -BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o +LIB_OBJS += $(OUTPUT)ui/helpline.o +LIB_OBJS += $(OUTPUT)ui/hist.o +LIB_OBJS += $(OUTPUT)ui/stdio/hist.o +BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o - # Benchmark modules BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o @@ -449,34 +471,73 @@ PYRF_OBJS += $(OUTPUT)util/xyarray.o -include config.mak.autogen -include config.mak -ifndef NO_DWARF -FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) -ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); +ifdef NO_LIBELF NO_DWARF := 1 -endif # Dwarf support -endif # NO_DWARF - --include arch/$(ARCH)/Makefile - -ifneq ($(OUTPUT),) - BASIC_CFLAGS += -I$(OUTPUT) -endif - + NO_DEMANGLE := 1 + NO_LIBUNWIND := 1 +else FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y) FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS) ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y) msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); else - msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel); + NO_LIBELF := 1 + NO_DWARF := 1 + NO_DEMANGLE := 1 endif endif +endif # NO_LIBELF + +ifndef NO_LIBUNWIND +# for linking with debug library, run like: +# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ +ifdef LIBUNWIND_DIR + LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include + LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib +endif + +FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) +ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND)),y) + msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); + NO_LIBUNWIND := 1 +endif # Libunwind support +endif # NO_LIBUNWIND + +-include arch/$(ARCH)/Makefile + +ifneq ($(OUTPUT),) + BASIC_CFLAGS += -I$(OUTPUT) +endif + +ifdef NO_LIBELF +BASIC_CFLAGS += -DNO_LIBELF_SUPPORT + +EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) + +# Remove ELF/DWARF dependent codes +LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS)) + +BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) + +# Use minimal symbol handling +LIB_OBJS += $(OUTPUT)util/symbol-minimal.o + +else # NO_LIBELF ifneq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y) BASIC_CFLAGS += -DLIBELF_NO_MMAP endif +FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) +ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 +endif # Dwarf support + ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); @@ -487,6 +548,29 @@ else LIB_OBJS += $(OUTPUT)util/dwarf-aux.o endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF +endif # NO_LIBELF + +ifdef NO_LIBUNWIND + BASIC_CFLAGS += -DNO_LIBUNWIND_SUPPORT +else + EXTLIBS += $(LIBUNWIND_LIBS) + BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS) + BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS) + LIB_OBJS += $(OUTPUT)util/unwind.o +endif + +ifdef NO_LIBAUDIT + BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT +else + FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit + ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT)),y) + msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); + BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT + else + BUILTIN_OBJS += $(OUTPUT)builtin-trace.o + EXTLIBS += -laudit + endif +endif ifdef NO_NEWT BASIC_CFLAGS += -DNO_NEWT_SUPPORT @@ -504,14 +588,13 @@ else LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o LIB_OBJS += $(OUTPUT)ui/browsers/hists.o LIB_OBJS += $(OUTPUT)ui/browsers/map.o - LIB_OBJS += $(OUTPUT)ui/helpline.o LIB_OBJS += $(OUTPUT)ui/progress.o LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/tui/setup.o LIB_OBJS += $(OUTPUT)ui/tui/util.o + LIB_OBJS += $(OUTPUT)ui/tui/helpline.o LIB_H += ui/browser.h LIB_H += ui/browsers/map.h - LIB_H += ui/helpline.h LIB_H += ui/keysyms.h LIB_H += ui/libslang.h LIB_H += ui/progress.h @@ -523,7 +606,7 @@ endif ifdef NO_GTK2 BASIC_CFLAGS += -DNO_GTK2_SUPPORT else - FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0) + FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); BASIC_CFLAGS += -DNO_GTK2_SUPPORT @@ -531,11 +614,12 @@ else ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y) BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR endif - BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0) - EXTLIBS += $(shell pkg-config --libs gtk+-2.0) + BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) + EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null) LIB_OBJS += $(OUTPUT)ui/gtk/browser.o LIB_OBJS += $(OUTPUT)ui/gtk/setup.o LIB_OBJS += $(OUTPUT)ui/gtk/util.o + LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o # Make sure that it'd be included only once. ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),) LIB_OBJS += $(OUTPUT)ui/setup.o @@ -644,7 +728,7 @@ else EXTLIBS += -liberty BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE else - FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd + FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD)) ifeq ($(has_bfd),y) EXTLIBS += -lbfd @@ -674,6 +758,13 @@ else endif endif +ifeq ($(NO_PERF_REGS),0) + ifeq ($(ARCH),x86) + LIB_H += arch/x86/include/perf_regs.h + endif +else + BASIC_CFLAGS += -DNO_PERF_REGS +endif ifdef NO_STRLCPY BASIC_CFLAGS += -DNO_STRLCPY @@ -683,6 +774,14 @@ else endif endif +ifdef NO_BACKTRACE + BASIC_CFLAGS += -DNO_BACKTRACE +else + ifneq ($(call try-cc,$(SOURCE_BACKTRACE),),y) + BASIC_CFLAGS += -DNO_BACKTRACE + endif +endif + ifdef ASCIIDOC8 export ASCIIDOC8 endif @@ -700,6 +799,7 @@ perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) prefix_SQ = $(subst ','\'',$(prefix)) +sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) @@ -767,10 +867,10 @@ $(OUTPUT)perf.o perf.spec \ # over the general rule for .o $(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -w $< + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -w $< $(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -w $< + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< @@ -842,7 +942,10 @@ $(LIB_FILE): $(LIB_OBJS) # libtraceevent.a $(LIBTRACEEVENT): - $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) $(COMMAND_O) libtraceevent.a + $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a + +$(LIBTRACEEVENT)-clean: + $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean help: @echo 'Perf make targets:' @@ -951,6 +1054,8 @@ install: all $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace' $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python' $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d' + $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' @@ -981,7 +1086,7 @@ quick-install-html: ### Cleaning rules -clean: +clean: $(LIBTRACEEVENT)-clean $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(RM) $(ALL_PROGRAMS) perf $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 744e629797be..815841c04eb2 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -2,4 +2,7 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif +ifndef NO_LIBUNWIND +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o +endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h new file mode 100644 index 000000000000..46fc9f15c6b3 --- /dev/null +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -0,0 +1,80 @@ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include "../../util/types.h" +#include "../../../../../arch/x86/include/asm/perf_regs.h" + +#ifndef ARCH_X86_64 +#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) +#else +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) +#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) +#endif +#define PERF_REG_IP PERF_REG_X86_IP +#define PERF_REG_SP PERF_REG_X86_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_X86_AX: + return "AX"; + case PERF_REG_X86_BX: + return "BX"; + case PERF_REG_X86_CX: + return "CX"; + case PERF_REG_X86_DX: + return "DX"; + case PERF_REG_X86_SI: + return "SI"; + case PERF_REG_X86_DI: + return "DI"; + case PERF_REG_X86_BP: + return "BP"; + case PERF_REG_X86_SP: + return "SP"; + case PERF_REG_X86_IP: + return "IP"; + case PERF_REG_X86_FLAGS: + return "FLAGS"; + case PERF_REG_X86_CS: + return "CS"; + case PERF_REG_X86_SS: + return "SS"; + case PERF_REG_X86_DS: + return "DS"; + case PERF_REG_X86_ES: + return "ES"; + case PERF_REG_X86_FS: + return "FS"; + case PERF_REG_X86_GS: + return "GS"; +#ifdef ARCH_X86_64 + case PERF_REG_X86_R8: + return "R8"; + case PERF_REG_X86_R9: + return "R9"; + case PERF_REG_X86_R10: + return "R10"; + case PERF_REG_X86_R11: + return "R11"; + case PERF_REG_X86_R12: + return "R12"; + case PERF_REG_X86_R13: + return "R13"; + case PERF_REG_X86_R14: + return "R14"; + case PERF_REG_X86_R15: + return "R15"; +#endif /* ARCH_X86_64 */ + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind.c new file mode 100644 index 000000000000..78d956eff96f --- /dev/null +++ b/tools/perf/arch/x86/util/unwind.c @@ -0,0 +1,111 @@ + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" + +#ifdef ARCH_X86_64 +int unwind__arch_reg_id(int regnum) +{ + int id; + + switch (regnum) { + case UNW_X86_64_RAX: + id = PERF_REG_X86_AX; + break; + case UNW_X86_64_RDX: + id = PERF_REG_X86_DX; + break; + case UNW_X86_64_RCX: + id = PERF_REG_X86_CX; + break; + case UNW_X86_64_RBX: + id = PERF_REG_X86_BX; + break; + case UNW_X86_64_RSI: + id = PERF_REG_X86_SI; + break; + case UNW_X86_64_RDI: + id = PERF_REG_X86_DI; + break; + case UNW_X86_64_RBP: + id = PERF_REG_X86_BP; + break; + case UNW_X86_64_RSP: + id = PERF_REG_X86_SP; + break; + case UNW_X86_64_R8: + id = PERF_REG_X86_R8; + break; + case UNW_X86_64_R9: + id = PERF_REG_X86_R9; + break; + case UNW_X86_64_R10: + id = PERF_REG_X86_R10; + break; + case UNW_X86_64_R11: + id = PERF_REG_X86_R11; + break; + case UNW_X86_64_R12: + id = PERF_REG_X86_R12; + break; + case UNW_X86_64_R13: + id = PERF_REG_X86_R13; + break; + case UNW_X86_64_R14: + id = PERF_REG_X86_R14; + break; + case UNW_X86_64_R15: + id = PERF_REG_X86_R15; + break; + case UNW_X86_64_RIP: + id = PERF_REG_X86_IP; + break; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return id; +} +#else +int unwind__arch_reg_id(int regnum) +{ + int id; + + switch (regnum) { + case UNW_X86_EAX: + id = PERF_REG_X86_AX; + break; + case UNW_X86_EDX: + id = PERF_REG_X86_DX; + break; + case UNW_X86_ECX: + id = PERF_REG_X86_CX; + break; + case UNW_X86_EBX: + id = PERF_REG_X86_BX; + break; + case UNW_X86_ESI: + id = PERF_REG_X86_SI; + break; + case UNW_X86_EDI: + id = PERF_REG_X86_DI; + break; + case UNW_X86_EBP: + id = PERF_REG_X86_BP; + break; + case UNW_X86_ESP: + id = PERF_REG_X86_SP; + break; + case UNW_X86_EIP: + id = PERF_REG_X86_IP; + break; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return id; +} +#endif /* ARCH_X86_64 */ diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion new file mode 100644 index 000000000000..1958fa539d0f --- /dev/null +++ b/tools/perf/bash_completion @@ -0,0 +1,26 @@ +# perf completion + +have perf && +_perf() +{ + local cur cmd + + COMPREPLY=() + _get_comp_words_by_ref cur prev + + cmd=${COMP_WORDS[0]} + + # List perf subcommands + if [ $COMP_CWORD -eq 1 ]; then + cmds=$($cmd --list-cmds) + COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) + # List possible events for -e option + elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then + cmds=$($cmd list --raw-dump) + COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) + # Fall down to list regular files + else + _filedir + fi +} && +complete -F _perf perf diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index a09bece6dad2..8f89998eeaf4 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -3,7 +3,8 @@ extern int bench_sched_messaging(int argc, const char **argv, const char *prefix); extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); -extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used); +extern int bench_mem_memcpy(int argc, const char **argv, + const char *prefix __maybe_unused); extern int bench_mem_memset(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_DEFAULT_STR "default" diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 02dad5d3359b..93c83e3cb4a7 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -177,7 +177,7 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) } while (0) int bench_mem_memcpy(int argc, const char **argv, - const char *prefix __used) + const char *prefix __maybe_unused) { int i; size_t len; diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index 350cc9557265..c6e4bc523492 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -171,7 +171,7 @@ static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) } while (0) int bench_mem_memset(int argc, const char **argv, - const char *prefix __used) + const char *prefix __maybe_unused) { int i; size_t len; diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index d1d1b30f99c1..cc1190a0849b 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -267,7 +267,7 @@ static const char * const bench_sched_message_usage[] = { }; int bench_sched_messaging(int argc, const char **argv, - const char *prefix __used) + const char *prefix __maybe_unused) { unsigned int i, total_children; struct timeval start, stop, diff; diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 0c7454f8b8a9..69cfba8d4c6c 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -43,7 +43,7 @@ static const char * const bench_sched_pipe_usage[] = { }; int bench_sched_pipe(int argc, const char **argv, - const char *prefix __used) + const char *prefix __maybe_unused) { int pipe_1[2], pipe_2[2]; int m = 0, i; @@ -55,14 +55,14 @@ int bench_sched_pipe(int argc, const char **argv, * discarding returned value of read(), write() * causes error in building environment for perf */ - int __used ret, wait_stat; - pid_t pid, retpid; + int __maybe_unused ret, wait_stat; + pid_t pid, retpid __maybe_unused; argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0); - assert(!pipe(pipe_1)); - assert(!pipe(pipe_2)); + BUG_ON(pipe(pipe_1)); + BUG_ON(pipe(pipe_2)); pid = fork(); assert(pid >= 0); diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 67522cf87405..9ea38540b873 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -239,7 +239,7 @@ static const char * const annotate_usage[] = { NULL }; -int cmd_annotate(int argc, const char **argv, const char *prefix __used) +int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_annotate annotate = { .tool = { @@ -282,6 +282,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "objdump", &objdump_path, "path", + "objdump binary to use for disassembly and annotations"), OPT_END() }; diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 1f3100216448..cae9a5fd2ecf 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -173,7 +173,7 @@ static void all_subsystem(void) all_suite(&subsystems[i]); } -int cmd_bench(int argc, const char **argv, const char *prefix __used) +int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) { int i, j, status = 0; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 29ad20e67919..83654557e108 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -43,15 +43,16 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir) } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__add_s(sbuild_id, debugdir, filename, false); + err = build_id_cache__add_s(sbuild_id, debugdir, filename, + false, false); if (verbose) pr_info("Adding %s %s: %s\n", sbuild_id, filename, err ? "FAIL" : "Ok"); return err; } -static int build_id_cache__remove_file(const char *filename __used, - const char *debugdir __used) +static int build_id_cache__remove_file(const char *filename __maybe_unused, + const char *debugdir __maybe_unused) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; @@ -119,7 +120,8 @@ static int __cmd_buildid_cache(void) return 0; } -int cmd_buildid_cache(int argc, const char **argv, const char *prefix __used) +int cmd_buildid_cache(int argc, const char **argv, + const char *prefix __maybe_unused) { argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 6b2bcfbde150..1159feeebb19 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -16,8 +16,6 @@ #include "util/session.h" #include "util/symbol.h" -#include <libelf.h> - static const char *input_name; static bool force; static bool show_kernel; @@ -71,7 +69,7 @@ static int perf_session__list_build_ids(void) { struct perf_session *session; - elf_version(EV_CURRENT); + symbol__elf_init(); session = perf_session__new(input_name, O_RDONLY, force, false, &build_id__mark_dso_hit_ops); @@ -105,7 +103,8 @@ static int __cmd_buildid_list(void) return perf_session__list_build_ids(); } -int cmd_buildid_list(int argc, const char **argv, const char *prefix __used) +int cmd_buildid_list(int argc, const char **argv, + const char *prefix __maybe_unused) { argc = parse_options(argc, argv, options, buildid_list_usage, 0); setup_pager(); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d29d350fb2b7..761f4197a9e2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -10,6 +10,7 @@ #include "util/event.h" #include "util/hist.h" #include "util/evsel.h" +#include "util/evlist.h" #include "util/session.h" #include "util/tool.h" #include "util/sort.h" @@ -24,11 +25,6 @@ static char diff__default_sort_order[] = "dso,symbol"; static bool force; static bool show_displacement; -struct perf_diff { - struct perf_tool tool; - struct perf_session *session; -}; - static int hists__add_entry(struct hists *self, struct addr_location *al, u64 period) { @@ -37,14 +33,12 @@ static int hists__add_entry(struct hists *self, return -ENOMEM; } -static int diff__process_sample_event(struct perf_tool *tool, +static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __used, + struct perf_evsel *evsel, struct machine *machine) { - struct perf_diff *_diff = container_of(tool, struct perf_diff, tool); - struct perf_session *session = _diff->session; struct addr_location al; if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { @@ -56,26 +50,24 @@ static int diff__process_sample_event(struct perf_tool *tool, if (al.filtered || al.sym == NULL) return 0; - if (hists__add_entry(&session->hists, &al, sample->period)) { + if (hists__add_entry(&evsel->hists, &al, sample->period)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } - session->hists.stats.total_period += sample->period; + evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_diff diff = { - .tool = { - .sample = diff__process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, - .lost = perf_event__process_lost, - .ordered_samples = true, - .ordering_requires_timestamps = true, - }, +static struct perf_tool tool = { + .sample = diff__process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .lost = perf_event__process_lost, + .ordered_samples = true, + .ordering_requires_timestamps = true, }; static void perf_session__insert_hist_entry_by_name(struct rb_root *root, @@ -146,34 +138,71 @@ static void hists__match(struct hists *older, struct hists *newer) } } +static struct perf_evsel *evsel_match(struct perf_evsel *evsel, + struct perf_evlist *evlist) +{ + struct perf_evsel *e; + + list_for_each_entry(e, &evlist->entries, node) + if (perf_evsel__match2(evsel, e)) + return e; + + return NULL; +} + static int __cmd_diff(void) { int ret, i; #define older (session[0]) #define newer (session[1]) struct perf_session *session[2]; + struct perf_evlist *evlist_new, *evlist_old; + struct perf_evsel *evsel; + bool first = true; older = perf_session__new(input_old, O_RDONLY, force, false, - &diff.tool); + &tool); newer = perf_session__new(input_new, O_RDONLY, force, false, - &diff.tool); + &tool); if (session[0] == NULL || session[1] == NULL) return -ENOMEM; for (i = 0; i < 2; ++i) { - diff.session = session[i]; - ret = perf_session__process_events(session[i], &diff.tool); + ret = perf_session__process_events(session[i], &tool); if (ret) goto out_delete; - hists__output_resort(&session[i]->hists); } - if (show_displacement) - hists__resort_entries(&older->hists); + evlist_old = older->evlist; + evlist_new = newer->evlist; + + list_for_each_entry(evsel, &evlist_new->entries, node) + hists__output_resort(&evsel->hists); + + list_for_each_entry(evsel, &evlist_old->entries, node) { + hists__output_resort(&evsel->hists); + + if (show_displacement) + hists__resort_entries(&evsel->hists); + } + + list_for_each_entry(evsel, &evlist_new->entries, node) { + struct perf_evsel *evsel_old; + + evsel_old = evsel_match(evsel, evlist_old); + if (!evsel_old) + continue; + + fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", + perf_evsel__name(evsel)); + + first = false; + + hists__match(&evsel_old->hists, &evsel->hists); + hists__fprintf(&evsel->hists, &evsel_old->hists, + show_displacement, true, 0, 0, stdout); + } - hists__match(&older->hists, &newer->hists); - hists__fprintf(&newer->hists, &older->hists, - show_displacement, true, 0, 0, stdout); out_delete: for (i = 0; i < 2; ++i) perf_session__delete(session[i]); @@ -213,7 +242,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_diff(int argc, const char **argv, const char *prefix __used) +int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) { sort_order = diff__default_sort_order; argc = parse_options(argc, argv, options, diff_usage, 0); @@ -235,6 +264,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __used) if (symbol__init() < 0) return -1; + perf_hpp__init(true, show_displacement); setup_sorting(diff_usage, options); setup_pager(); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 0dd5a058f766..1fb164164fd0 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -113,7 +113,7 @@ static const char * const evlist_usage[] = { NULL }; -int cmd_evlist(int argc, const char **argv, const char *prefix __used) +int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_attr_details details = { .verbose = false, }; const char *input_name = NULL; diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 6d5a8a7faf48..25c8b942ff85 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -24,13 +24,14 @@ static struct man_viewer_info_list { } *man_viewer_info_list; enum help_format { + HELP_FORMAT_NONE, HELP_FORMAT_MAN, HELP_FORMAT_INFO, HELP_FORMAT_WEB, }; static bool show_all = false; -static enum help_format help_format = HELP_FORMAT_MAN; +static enum help_format help_format = HELP_FORMAT_NONE; static struct option builtin_help_options[] = { OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN), @@ -54,7 +55,9 @@ static enum help_format parse_help_format(const char *format) return HELP_FORMAT_INFO; if (!strcmp(format, "web") || !strcmp(format, "html")) return HELP_FORMAT_WEB; - die("unrecognized help format '%s'", format); + + pr_err("unrecognized help format '%s'", format); + return HELP_FORMAT_NONE; } static const char *get_man_viewer_info(const char *name) @@ -259,6 +262,8 @@ static int perf_help_config(const char *var, const char *value, void *cb) if (!value) return config_error_nonbool(var); help_format = parse_help_format(value); + if (help_format == HELP_FORMAT_NONE) + return -1; return 0; } if (!strcmp(var, "man.viewer")) { @@ -352,7 +357,7 @@ static void exec_viewer(const char *name, const char *page) warning("'%s': unknown man viewer.", name); } -static void show_man_page(const char *perf_cmd) +static int show_man_page(const char *perf_cmd) { struct man_viewer_list *viewer; const char *page = cmd_to_page(perf_cmd); @@ -365,28 +370,35 @@ static void show_man_page(const char *perf_cmd) if (fallback) exec_viewer(fallback, page); exec_viewer("man", page); - die("no man viewer handled the request"); + + pr_err("no man viewer handled the request"); + return -1; } -static void show_info_page(const char *perf_cmd) +static int show_info_page(const char *perf_cmd) { const char *page = cmd_to_page(perf_cmd); setenv("INFOPATH", system_path(PERF_INFO_PATH), 1); execlp("info", "info", "perfman", page, NULL); + return -1; } -static void get_html_page_path(struct strbuf *page_path, const char *page) +static int get_html_page_path(struct strbuf *page_path, const char *page) { struct stat st; const char *html_path = system_path(PERF_HTML_PATH); /* Check that we have a perf documentation directory. */ if (stat(mkpath("%s/perf.html", html_path), &st) - || !S_ISREG(st.st_mode)) - die("'%s': not a documentation directory.", html_path); + || !S_ISREG(st.st_mode)) { + pr_err("'%s': not a documentation directory.", html_path); + return -1; + } strbuf_init(page_path, 0); strbuf_addf(page_path, "%s/%s.html", html_path, page); + + return 0; } /* @@ -401,19 +413,23 @@ static void open_html(const char *path) } #endif -static void show_html_page(const char *perf_cmd) +static int show_html_page(const char *perf_cmd) { const char *page = cmd_to_page(perf_cmd); struct strbuf page_path; /* it leaks but we exec bellow */ - get_html_page_path(&page_path, page); + if (get_html_page_path(&page_path, page) != 0) + return -1; open_html(page_path.buf); + + return 0; } -int cmd_help(int argc, const char **argv, const char *prefix __used) +int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) { const char *alias; + int rc = 0; load_command_list("perf-", &main_cmds, &other_cmds); @@ -444,16 +460,20 @@ int cmd_help(int argc, const char **argv, const char *prefix __used) switch (help_format) { case HELP_FORMAT_MAN: - show_man_page(argv[0]); + rc = show_man_page(argv[0]); break; case HELP_FORMAT_INFO: - show_info_page(argv[0]); + rc = show_info_page(argv[0]); break; case HELP_FORMAT_WEB: - show_html_page(argv[0]); + rc = show_html_page(argv[0]); + break; + case HELP_FORMAT_NONE: + /* fall-through */ default: + rc = -1; break; } - return 0; + return rc; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 3beab489afc5..1eaa6617c814 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -17,9 +17,9 @@ static char const *input_name = "-"; static bool inject_build_ids; -static int perf_event__repipe_synth(struct perf_tool *tool __used, +static int perf_event__repipe_synth(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct machine *machine __used) + struct machine *machine __maybe_unused) { uint32_t size; void *buf = event; @@ -40,7 +40,8 @@ static int perf_event__repipe_synth(struct perf_tool *tool __used, static int perf_event__repipe_op2_synth(struct perf_tool *tool, union perf_event *event, - struct perf_session *session __used) + struct perf_session *session + __maybe_unused) { return perf_event__repipe_synth(tool, event, NULL); } @@ -52,13 +53,14 @@ static int perf_event__repipe_event_type_synth(struct perf_tool *tool, } static int perf_event__repipe_tracing_data_synth(union perf_event *event, - struct perf_session *session __used) + struct perf_session *session + __maybe_unused) { return perf_event__repipe_synth(NULL, event, NULL); } static int perf_event__repipe_attr(union perf_event *event, - struct perf_evlist **pevlist __used) + struct perf_evlist **pevlist __maybe_unused) { int ret; ret = perf_event__process_attr(event, pevlist); @@ -70,7 +72,7 @@ static int perf_event__repipe_attr(union perf_event *event, static int perf_event__repipe(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample __maybe_unused, struct machine *machine) { return perf_event__repipe_synth(tool, event, machine); @@ -78,8 +80,8 @@ static int perf_event__repipe(struct perf_tool *tool, static int perf_event__repipe_sample(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __used, - struct perf_evsel *evsel __used, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, struct machine *machine) { return perf_event__repipe_synth(tool, event, machine); @@ -163,7 +165,7 @@ static int dso__inject_build_id(struct dso *self, struct perf_tool *tool, static int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __used, + struct perf_evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; @@ -191,10 +193,13 @@ static int perf_event__inject_buildid(struct perf_tool *tool, * If this fails, too bad, let the other side * account this as unresolved. */ - } else + } else { +#ifndef NO_LIBELF_SUPPORT pr_warning("no symbols found in %s, maybe " "install a debug package?\n", al.map->dso->long_name); +#endif + } } } @@ -221,7 +226,7 @@ struct perf_tool perf_inject = { extern volatile int session_done; -static void sig_handler(int sig __attribute__((__unused__))) +static void sig_handler(int sig __maybe_unused) { session_done = 1; } @@ -264,7 +269,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_inject(int argc, const char **argv, const char *prefix __used) +int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) { argc = parse_options(argc, argv, options, report_usage, 0); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index ce35015f2dc6..bc912c68f49a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1,6 +1,8 @@ #include "builtin.h" #include "perf.h" +#include "util/evlist.h" +#include "util/evsel.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" @@ -57,46 +59,52 @@ static unsigned long nr_allocs, nr_cross_allocs; #define PATH_SYS_NODE "/sys/devices/system/node" -struct perf_kmem { - struct perf_tool tool; - struct perf_session *session; -}; - -static void init_cpunode_map(void) +static int init_cpunode_map(void) { FILE *fp; - int i; + int i, err = -1; fp = fopen("/sys/devices/system/cpu/kernel_max", "r"); if (!fp) { max_cpu_num = 4096; - return; + return 0; + } + + if (fscanf(fp, "%d", &max_cpu_num) < 1) { + pr_err("Failed to read 'kernel_max' from sysfs"); + goto out_close; } - if (fscanf(fp, "%d", &max_cpu_num) < 1) - die("Failed to read 'kernel_max' from sysfs"); max_cpu_num++; cpunode_map = calloc(max_cpu_num, sizeof(int)); - if (!cpunode_map) - die("calloc"); + if (!cpunode_map) { + pr_err("%s: calloc failed\n", __func__); + goto out_close; + } + for (i = 0; i < max_cpu_num; i++) cpunode_map[i] = -1; + + err = 0; +out_close: fclose(fp); + return err; } -static void setup_cpunode_map(void) +static int setup_cpunode_map(void) { struct dirent *dent1, *dent2; DIR *dir1, *dir2; unsigned int cpu, mem; char buf[PATH_MAX]; - init_cpunode_map(); + if (init_cpunode_map()) + return -1; dir1 = opendir(PATH_SYS_NODE); if (!dir1) - return; + return -1; while ((dent1 = readdir(dir1)) != NULL) { if (dent1->d_type != DT_DIR || @@ -116,10 +124,11 @@ static void setup_cpunode_map(void) closedir(dir2); } closedir(dir1); + return 0; } -static void insert_alloc_stat(unsigned long call_site, unsigned long ptr, - int bytes_req, int bytes_alloc, int cpu) +static int insert_alloc_stat(unsigned long call_site, unsigned long ptr, + int bytes_req, int bytes_alloc, int cpu) { struct rb_node **node = &root_alloc_stat.rb_node; struct rb_node *parent = NULL; @@ -143,8 +152,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr, data->bytes_alloc += bytes_alloc; } else { data = malloc(sizeof(*data)); - if (!data) - die("malloc"); + if (!data) { + pr_err("%s: malloc failed\n", __func__); + return -1; + } data->ptr = ptr; data->pingpong = 0; data->hit = 1; @@ -156,9 +167,10 @@ static void insert_alloc_stat(unsigned long call_site, unsigned long ptr, } data->call_site = call_site; data->alloc_cpu = cpu; + return 0; } -static void insert_caller_stat(unsigned long call_site, +static int insert_caller_stat(unsigned long call_site, int bytes_req, int bytes_alloc) { struct rb_node **node = &root_caller_stat.rb_node; @@ -183,8 +195,10 @@ static void insert_caller_stat(unsigned long call_site, data->bytes_alloc += bytes_alloc; } else { data = malloc(sizeof(*data)); - if (!data) - die("malloc"); + if (!data) { + pr_err("%s: malloc failed\n", __func__); + return -1; + } data->call_site = call_site; data->pingpong = 0; data->hit = 1; @@ -194,39 +208,43 @@ static void insert_caller_stat(unsigned long call_site, rb_link_node(&data->node, parent, node); rb_insert_color(&data->node, &root_caller_stat); } + + return 0; } -static void process_alloc_event(void *data, - struct event_format *event, - int cpu, - u64 timestamp __used, - struct thread *thread __used, - int node) +static int perf_evsel__process_alloc_event(struct perf_evsel *evsel, + struct perf_sample *sample) { - unsigned long call_site; - unsigned long ptr; - int bytes_req; - int bytes_alloc; - int node1, node2; - - ptr = raw_field_value(event, "ptr", data); - call_site = raw_field_value(event, "call_site", data); - bytes_req = raw_field_value(event, "bytes_req", data); - bytes_alloc = raw_field_value(event, "bytes_alloc", data); + unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"), + call_site = perf_evsel__intval(evsel, sample, "call_site"); + int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"), + bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc"); - insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, cpu); - insert_caller_stat(call_site, bytes_req, bytes_alloc); + if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) || + insert_caller_stat(call_site, bytes_req, bytes_alloc)) + return -1; total_requested += bytes_req; total_allocated += bytes_alloc; - if (node) { - node1 = cpunode_map[cpu]; - node2 = raw_field_value(event, "node", data); + nr_allocs++; + return 0; +} + +static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel, + struct perf_sample *sample) +{ + int ret = perf_evsel__process_alloc_event(evsel, sample); + + if (!ret) { + int node1 = cpunode_map[sample->cpu], + node2 = perf_evsel__intval(evsel, sample, "node"); + if (node1 != node2) nr_cross_allocs++; } - nr_allocs++; + + return ret; } static int ptr_cmp(struct alloc_stat *, struct alloc_stat *); @@ -257,66 +275,37 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr, return NULL; } -static void process_free_event(void *data, - struct event_format *event, - int cpu, - u64 timestamp __used, - struct thread *thread __used) +static int perf_evsel__process_free_event(struct perf_evsel *evsel, + struct perf_sample *sample) { - unsigned long ptr; + unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"); struct alloc_stat *s_alloc, *s_caller; - ptr = raw_field_value(event, "ptr", data); - s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp); if (!s_alloc) - return; + return 0; - if (cpu != s_alloc->alloc_cpu) { + if ((short)sample->cpu != s_alloc->alloc_cpu) { s_alloc->pingpong++; s_caller = search_alloc_stat(0, s_alloc->call_site, &root_caller_stat, callsite_cmp); - assert(s_caller); + if (!s_caller) + return -1; s_caller->pingpong++; } s_alloc->alloc_cpu = -1; -} -static void process_raw_event(struct perf_tool *tool, - union perf_event *raw_event __used, void *data, - int cpu, u64 timestamp, struct thread *thread) -{ - struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool); - struct event_format *event; - int type; - - type = trace_parse_common_type(kmem->session->pevent, data); - event = pevent_find_event(kmem->session->pevent, type); - - if (!strcmp(event->name, "kmalloc") || - !strcmp(event->name, "kmem_cache_alloc")) { - process_alloc_event(data, event, cpu, timestamp, thread, 0); - return; - } - - if (!strcmp(event->name, "kmalloc_node") || - !strcmp(event->name, "kmem_cache_alloc_node")) { - process_alloc_event(data, event, cpu, timestamp, thread, 1); - return; - } - - if (!strcmp(event->name, "kfree") || - !strcmp(event->name, "kmem_cache_free")) { - process_free_event(data, event, cpu, timestamp, thread); - return; - } + return 0; } -static int process_sample_event(struct perf_tool *tool, +typedef int (*tracepoint_handler)(struct perf_evsel *evsel, + struct perf_sample *sample); + +static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __used, + struct perf_evsel *evsel, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, event->ip.pid); @@ -329,18 +318,18 @@ static int process_sample_event(struct perf_tool *tool, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - process_raw_event(tool, event, sample->raw_data, sample->cpu, - sample->time, thread); + if (evsel->handler.func != NULL) { + tracepoint_handler f = evsel->handler.func; + return f(evsel, sample); + } return 0; } -static struct perf_kmem perf_kmem = { - .tool = { - .sample = process_sample_event, - .comm = perf_event__process_comm, - .ordered_samples = true, - }, +static struct perf_tool perf_kmem = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, }; static double fragmentation(unsigned long n_req, unsigned long n_alloc) @@ -496,22 +485,32 @@ static int __cmd_kmem(void) { int err = -EINVAL; struct perf_session *session; - - session = perf_session__new(input_name, O_RDONLY, 0, false, - &perf_kmem.tool); + const struct perf_evsel_str_handler kmem_tracepoints[] = { + { "kmem:kmalloc", perf_evsel__process_alloc_event, }, + { "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, }, + { "kmem:kmalloc_node", perf_evsel__process_alloc_node_event, }, + { "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, }, + { "kmem:kfree", perf_evsel__process_free_event, }, + { "kmem:kmem_cache_free", perf_evsel__process_free_event, }, + }; + + session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem); if (session == NULL) return -ENOMEM; - perf_kmem.session = session; - if (perf_session__create_kernel_maps(session) < 0) goto out_delete; if (!perf_session__has_traces(session, "kmem record")) goto out_delete; + if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) { + pr_err("Initializing perf session tracepoint handlers failed\n"); + return -1; + } + setup_pager(); - err = perf_session__process_events(session, &perf_kmem.tool); + err = perf_session__process_events(session, &perf_kmem); if (err != 0) goto out_delete; sort_result(); @@ -635,8 +634,10 @@ static int sort_dimension__add(const char *tok, struct list_head *list) for (i = 0; i < NUM_AVAIL_SORTS; i++) { if (!strcmp(avail_sorts[i]->name, tok)) { sort = malloc(sizeof(*sort)); - if (!sort) - die("malloc"); + if (!sort) { + pr_err("%s: malloc failed\n", __func__); + return -1; + } memcpy(sort, avail_sorts[i], sizeof(*sort)); list_add_tail(&sort->list, list); return 0; @@ -651,8 +652,10 @@ static int setup_sorting(struct list_head *sort_list, const char *arg) char *tok; char *str = strdup(arg); - if (!str) - die("strdup"); + if (!str) { + pr_err("%s: strdup failed\n", __func__); + return -1; + } while (true) { tok = strsep(&str, ","); @@ -669,8 +672,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg) return 0; } -static int parse_sort_opt(const struct option *opt __used, - const char *arg, int unset __used) +static int parse_sort_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) { if (!arg) return -1; @@ -683,22 +686,24 @@ static int parse_sort_opt(const struct option *opt __used, return 0; } -static int parse_caller_opt(const struct option *opt __used, - const char *arg __used, int unset __used) +static int parse_caller_opt(const struct option *opt __maybe_unused, + const char *arg __maybe_unused, + int unset __maybe_unused) { caller_flag = (alloc_flag + 1); return 0; } -static int parse_alloc_opt(const struct option *opt __used, - const char *arg __used, int unset __used) +static int parse_alloc_opt(const struct option *opt __maybe_unused, + const char *arg __maybe_unused, + int unset __maybe_unused) { alloc_flag = (caller_flag + 1); return 0; } -static int parse_line_opt(const struct option *opt __used, - const char *arg, int unset __used) +static int parse_line_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) { int lines; @@ -768,7 +773,7 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -int cmd_kmem(int argc, const char **argv, const char *prefix __used) +int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) { argc = parse_options(argc, argv, kmem_options, kmem_usage, 0); @@ -780,7 +785,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used) if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strcmp(argv[0], "stat")) { - setup_cpunode_map(); + if (setup_cpunode_map()) + return -1; if (list_empty(&caller_sort)) setup_sorting(&caller_sort, default_sort_order); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 9fc6e0fa3dce..a28c9cad9048 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1,6 +1,7 @@ #include "builtin.h" #include "perf.h" +#include "util/evsel.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" @@ -10,8 +11,10 @@ #include "util/parse-options.h" #include "util/trace-event.h" - #include "util/debug.h" +#include "util/debugfs.h" +#include "util/tool.h" +#include "util/stat.h" #include <sys/prctl.h> @@ -19,11 +22,836 @@ #include <pthread.h> #include <math.h> -static const char *file_name; +#include "../../arch/x86/include/asm/svm.h" +#include "../../arch/x86/include/asm/vmx.h" +#include "../../arch/x86/include/asm/kvm.h" + +struct event_key { + #define INVALID_KEY (~0ULL) + u64 key; + int info; +}; + +struct kvm_events_ops { + bool (*is_begin_event)(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key); + bool (*is_end_event)(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key); + void (*decode_key)(struct event_key *key, char decode[20]); + const char *name; +}; + +static void exit_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = perf_evsel__intval(evsel, sample, "exit_reason"); +} + +static bool kvm_exit_event(struct perf_evsel *evsel) +{ + return !strcmp(evsel->name, "kvm:kvm_exit"); +} + +static bool exit_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (kvm_exit_event(evsel)) { + exit_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool kvm_entry_event(struct perf_evsel *evsel) +{ + return !strcmp(evsel->name, "kvm:kvm_entry"); +} + +static bool exit_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +struct exit_reasons_table { + unsigned long exit_code; + const char *reason; +}; + +struct exit_reasons_table vmx_exit_reasons[] = { + VMX_EXIT_REASONS +}; + +struct exit_reasons_table svm_exit_reasons[] = { + SVM_EXIT_REASONS +}; + +static int cpu_isa; + +static const char *get_exit_reason(u64 exit_code) +{ + int table_size = ARRAY_SIZE(svm_exit_reasons); + struct exit_reasons_table *table = svm_exit_reasons; + + if (cpu_isa == 1) { + table = vmx_exit_reasons; + table_size = ARRAY_SIZE(vmx_exit_reasons); + } + + while (table_size--) { + if (table->exit_code == exit_code) + return table->reason; + table++; + } + + pr_err("unknown kvm exit code:%lld on %s\n", + (unsigned long long)exit_code, cpu_isa ? "VMX" : "SVM"); + return "UNKNOWN"; +} + +static void exit_event_decode_key(struct event_key *key, char decode[20]) +{ + const char *exit_reason = get_exit_reason(key->key); + + scnprintf(decode, 20, "%s", exit_reason); +} + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + + /* + * For the mmio events, we treat: + * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry + * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). + */ +static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "gpa"); + key->info = perf_evsel__intval(evsel, sample, "type"); +} + +#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 +#define KVM_TRACE_MMIO_READ 1 +#define KVM_TRACE_MMIO_WRITE 2 + +static bool mmio_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + /* MMIO read begin event in kernel. */ + if (kvm_exit_event(evsel)) + return true; + + /* MMIO write begin event in kernel. */ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + /* MMIO write end event in kernel. */ + if (kvm_entry_event(evsel)) + return true; + + /* MMIO read end event in kernel.*/ + if (!strcmp(evsel->name, "kvm:kvm_mmio") && + perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static void mmio_event_decode_key(struct event_key *key, char decode[20]) +{ + scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key, + key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); +} + +static struct kvm_events_ops mmio_events = { + .is_begin_event = mmio_event_begin, + .is_end_event = mmio_event_end, + .decode_key = mmio_event_decode_key, + .name = "MMIO Access" +}; + + /* The time of emulation pio access is from kvm_pio to kvm_entry. */ +static void ioport_event_get_key(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = perf_evsel__intval(evsel, sample, "port"); + key->info = perf_evsel__intval(evsel, sample, "rw"); +} + +static bool ioport_event_begin(struct perf_evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (!strcmp(evsel->name, "kvm:kvm_pio")) { + ioport_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool ioport_event_end(struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static void ioport_event_decode_key(struct event_key *key, char decode[20]) +{ + scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key, + key->info ? "POUT" : "PIN"); +} + +static struct kvm_events_ops ioport_events = { + .is_begin_event = ioport_event_begin, + .is_end_event = ioport_event_end, + .decode_key = ioport_event_decode_key, + .name = "IO Port Access" +}; + +static const char *report_event = "vmexit"; +struct kvm_events_ops *events_ops; + +static bool register_kvm_events_ops(void) +{ + bool ret = true; + + if (!strcmp(report_event, "vmexit")) + events_ops = &exit_events; + else if (!strcmp(report_event, "mmio")) + events_ops = &mmio_events; + else if (!strcmp(report_event, "ioport")) + events_ops = &ioport_events; + else { + pr_err("Unknown report event:%s\n", report_event); + ret = false; + } + + return ret; +} + +struct kvm_event_stats { + u64 time; + struct stats stats; +}; + +struct kvm_event { + struct list_head hash_entry; + struct rb_node rb; + + struct event_key key; + + struct kvm_event_stats total; + + #define DEFAULT_VCPU_NUM 8 + int max_vcpu; + struct kvm_event_stats *vcpu; +}; + +struct vcpu_event_record { + int vcpu_id; + u64 start_time; + struct kvm_event *last_event; +}; + +#define EVENTS_BITS 12 +#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) + +static u64 total_time; +static u64 total_count; +static struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + +static void init_kvm_event_record(void) +{ + int i; + + for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++) + INIT_LIST_HEAD(&kvm_events_cache[i]); +} + +static int kvm_events_hash_fn(u64 key) +{ + return key & (EVENTS_CACHE_SIZE - 1); +} + +static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) +{ + int old_max_vcpu = event->max_vcpu; + + if (vcpu_id < event->max_vcpu) + return true; + + while (event->max_vcpu <= vcpu_id) + event->max_vcpu += DEFAULT_VCPU_NUM; + + event->vcpu = realloc(event->vcpu, + event->max_vcpu * sizeof(*event->vcpu)); + if (!event->vcpu) { + pr_err("Not enough memory\n"); + return false; + } + + memset(event->vcpu + old_max_vcpu, 0, + (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu)); + return true; +} + +static struct kvm_event *kvm_alloc_init_event(struct event_key *key) +{ + struct kvm_event *event; + + event = zalloc(sizeof(*event)); + if (!event) { + pr_err("Not enough memory\n"); + return NULL; + } + + event->key = *key; + return event; +} + +static struct kvm_event *find_create_kvm_event(struct event_key *key) +{ + struct kvm_event *event; + struct list_head *head; + + BUG_ON(key->key == INVALID_KEY); + + head = &kvm_events_cache[kvm_events_hash_fn(key->key)]; + list_for_each_entry(event, head, hash_entry) + if (event->key.key == key->key && event->key.info == key->info) + return event; + + event = kvm_alloc_init_event(key); + if (!event) + return NULL; + + list_add(&event->hash_entry, head); + return event; +} + +static bool handle_begin_event(struct vcpu_event_record *vcpu_record, + struct event_key *key, u64 timestamp) +{ + struct kvm_event *event = NULL; + + if (key->key != INVALID_KEY) + event = find_create_kvm_event(key); + + vcpu_record->last_event = event; + vcpu_record->start_time = timestamp; + return true; +} + +static void +kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff) +{ + kvm_stats->time += time_diff; + update_stats(&kvm_stats->stats, time_diff); +} + +static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event) +{ + struct kvm_event_stats *kvm_stats = &event->total; + + if (vcpu_id != -1) + kvm_stats = &event->vcpu[vcpu_id]; + + return rel_stddev_stats(stddev_stats(&kvm_stats->stats), + avg_stats(&kvm_stats->stats)); +} + +static bool update_kvm_event(struct kvm_event *event, int vcpu_id, + u64 time_diff) +{ + kvm_update_event_stats(&event->total, time_diff); + + if (!kvm_event_expand(event, vcpu_id)) + return false; + + kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff); + return true; +} + +static bool handle_end_event(struct vcpu_event_record *vcpu_record, + struct event_key *key, u64 timestamp) +{ + struct kvm_event *event; + u64 time_begin, time_diff; + + event = vcpu_record->last_event; + time_begin = vcpu_record->start_time; + + /* The begin event is not caught. */ + if (!time_begin) + return true; + + /* + * In some case, the 'begin event' only records the start timestamp, + * the actual event is recognized in the 'end event' (e.g. mmio-event). + */ + + /* Both begin and end events did not get the key. */ + if (!event && key->key == INVALID_KEY) + return true; + + if (!event) + event = find_create_kvm_event(key); + + if (!event) + return false; + + vcpu_record->last_event = NULL; + vcpu_record->start_time = 0; + + BUG_ON(timestamp < time_begin); + + time_diff = timestamp - time_begin; + return update_kvm_event(event, vcpu_record->vcpu_id, time_diff); +} + +static +struct vcpu_event_record *per_vcpu_record(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + /* Only kvm_entry records vcpu id. */ + if (!thread->priv && kvm_entry_event(evsel)) { + struct vcpu_event_record *vcpu_record; + + vcpu_record = zalloc(sizeof(*vcpu_record)); + if (!vcpu_record) { + pr_err("%s: Not enough memory\n", __func__); + return NULL; + } + + vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id"); + thread->priv = vcpu_record; + } + + return thread->priv; +} + +static bool handle_kvm_event(struct thread *thread, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + struct vcpu_event_record *vcpu_record; + struct event_key key = {.key = INVALID_KEY}; + + vcpu_record = per_vcpu_record(thread, evsel, sample); + if (!vcpu_record) + return true; + + if (events_ops->is_begin_event(evsel, sample, &key)) + return handle_begin_event(vcpu_record, &key, sample->time); + + if (events_ops->is_end_event(evsel, sample, &key)) + return handle_end_event(vcpu_record, &key, sample->time); + + return true; +} + +typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); +struct kvm_event_key { + const char *name; + key_cmp_fun key; +}; + +static int trace_vcpu = -1; +#define GET_EVENT_KEY(func, field) \ +static u64 get_event_ ##func(struct kvm_event *event, int vcpu) \ +{ \ + if (vcpu == -1) \ + return event->total.field; \ + \ + if (vcpu >= event->max_vcpu) \ + return 0; \ + \ + return event->vcpu[vcpu].field; \ +} + +#define COMPARE_EVENT_KEY(func, field) \ +GET_EVENT_KEY(func, field) \ +static int compare_kvm_event_ ## func(struct kvm_event *one, \ + struct kvm_event *two, int vcpu)\ +{ \ + return get_event_ ##func(one, vcpu) > \ + get_event_ ##func(two, vcpu); \ +} + +GET_EVENT_KEY(time, time); +COMPARE_EVENT_KEY(count, stats.n); +COMPARE_EVENT_KEY(mean, stats.mean); + +#define DEF_SORT_NAME_KEY(name, compare_key) \ + { #name, compare_kvm_event_ ## compare_key } + +static struct kvm_event_key keys[] = { + DEF_SORT_NAME_KEY(sample, count), + DEF_SORT_NAME_KEY(time, mean), + { NULL, NULL } +}; + +static const char *sort_key = "sample"; +static key_cmp_fun compare; + +static bool select_key(void) +{ + int i; + + for (i = 0; keys[i].name; i++) { + if (!strcmp(keys[i].name, sort_key)) { + compare = keys[i].key; + return true; + } + } + + pr_err("Unknown compare key:%s\n", sort_key); + return false; +} + +static struct rb_root result; +static void insert_to_result(struct kvm_event *event, key_cmp_fun bigger, + int vcpu) +{ + struct rb_node **rb = &result.rb_node; + struct rb_node *parent = NULL; + struct kvm_event *p; + + while (*rb) { + p = container_of(*rb, struct kvm_event, rb); + parent = *rb; + + if (bigger(event, p, vcpu)) + rb = &(*rb)->rb_left; + else + rb = &(*rb)->rb_right; + } + + rb_link_node(&event->rb, parent, rb); + rb_insert_color(&event->rb, &result); +} + +static void update_total_count(struct kvm_event *event, int vcpu) +{ + total_count += get_event_count(event, vcpu); + total_time += get_event_time(event, vcpu); +} + +static bool event_is_valid(struct kvm_event *event, int vcpu) +{ + return !!get_event_count(event, vcpu); +} + +static void sort_result(int vcpu) +{ + unsigned int i; + struct kvm_event *event; + + for (i = 0; i < EVENTS_CACHE_SIZE; i++) + list_for_each_entry(event, &kvm_events_cache[i], hash_entry) + if (event_is_valid(event, vcpu)) { + update_total_count(event, vcpu); + insert_to_result(event, compare, vcpu); + } +} + +/* returns left most element of result, and erase it */ +static struct kvm_event *pop_from_result(void) +{ + struct rb_node *node = rb_first(&result); + + if (!node) + return NULL; + + rb_erase(node, &result); + return container_of(node, struct kvm_event, rb); +} + +static void print_vcpu_info(int vcpu) +{ + pr_info("Analyze events for "); + + if (vcpu == -1) + pr_info("all VCPUs:\n\n"); + else + pr_info("VCPU %d:\n\n", vcpu); +} + +static void print_result(int vcpu) +{ + char decode[20]; + struct kvm_event *event; + + pr_info("\n\n"); + print_vcpu_info(vcpu); + pr_info("%20s ", events_ops->name); + pr_info("%10s ", "Samples"); + pr_info("%9s ", "Samples%"); + + pr_info("%9s ", "Time%"); + pr_info("%16s ", "Avg time"); + pr_info("\n\n"); + + while ((event = pop_from_result())) { + u64 ecount, etime; + + ecount = get_event_count(event, vcpu); + etime = get_event_time(event, vcpu); + + events_ops->decode_key(&event->key, decode); + pr_info("%20s ", decode); + pr_info("%10llu ", (unsigned long long)ecount); + pr_info("%8.2f%% ", (double)ecount / total_count * 100); + pr_info("%8.2f%% ", (double)etime / total_time * 100); + pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3, + kvm_event_rel_stddev(vcpu, event)); + pr_info("\n"); + } + + pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n", + (unsigned long long)total_count, total_time / 1e3); +} + +static int process_sample_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct thread *thread = machine__findnew_thread(machine, sample->tid); + + if (thread == NULL) { + pr_debug("problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (!handle_kvm_event(thread, evsel, sample)) + return -1; + + return 0; +} + +static struct perf_tool eops = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, +}; + +static int get_cpu_isa(struct perf_session *session) +{ + char *cpuid = session->header.env.cpuid; + int isa; + + if (strstr(cpuid, "Intel")) + isa = 1; + else if (strstr(cpuid, "AMD")) + isa = 0; + else { + pr_err("CPU %s is not supported.\n", cpuid); + isa = -ENOTSUP; + } + + return isa; +} + +static const char *file_name; + +static int read_events(void) +{ + struct perf_session *kvm_session; + int ret; + + kvm_session = perf_session__new(file_name, O_RDONLY, 0, false, &eops); + if (!kvm_session) { + pr_err("Initializing perf session failed\n"); + return -EINVAL; + } + + if (!perf_session__has_traces(kvm_session, "kvm record")) + return -EINVAL; + + /* + * Do not use 'isa' recorded in kvm_exit tracepoint since it is not + * traced in the old kernel. + */ + ret = get_cpu_isa(kvm_session); + + if (ret < 0) + return ret; + + cpu_isa = ret; + + return perf_session__process_events(kvm_session, &eops); +} + +static bool verify_vcpu(int vcpu) +{ + if (vcpu != -1 && vcpu < 0) { + pr_err("Invalid vcpu:%d.\n", vcpu); + return false; + } + + return true; +} + +static int kvm_events_report_vcpu(int vcpu) +{ + int ret = -EINVAL; + + if (!verify_vcpu(vcpu)) + goto exit; + + if (!select_key()) + goto exit; + + if (!register_kvm_events_ops()) + goto exit; + + init_kvm_event_record(); + setup_pager(); + + ret = read_events(); + if (ret) + goto exit; + + sort_result(vcpu); + print_result(vcpu); +exit: + return ret; +} + +static const char * const record_args[] = { + "record", + "-R", + "-f", + "-m", "1024", + "-c", "1", + "-e", "kvm:kvm_entry", + "-e", "kvm:kvm_exit", + "-e", "kvm:kvm_mmio", + "-e", "kvm:kvm_pio", +}; + +#define STRDUP_FAIL_EXIT(s) \ + ({ char *_p; \ + _p = strdup(s); \ + if (!_p) \ + return -ENOMEM; \ + _p; \ + }) + +static int kvm_events_record(int argc, const char **argv) +{ + unsigned int rec_argc, i, j; + const char **rec_argv; + + rec_argc = ARRAY_SIZE(record_args) + argc + 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + + if (rec_argv == NULL) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(record_args); i++) + rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]); + + rec_argv[i++] = STRDUP_FAIL_EXIT("-o"); + rec_argv[i++] = STRDUP_FAIL_EXIT(file_name); + + for (j = 1; j < (unsigned int)argc; j++, i++) + rec_argv[i] = argv[j]; + + return cmd_record(i, rec_argv, NULL); +} + +static const char * const kvm_events_report_usage[] = { + "perf kvm stat report [<options>]", + NULL +}; + +static const struct option kvm_events_report_options[] = { + OPT_STRING(0, "event", &report_event, "report event", + "event for reporting: vmexit, mmio, ioport"), + OPT_INTEGER(0, "vcpu", &trace_vcpu, + "vcpu id to report"), + OPT_STRING('k', "key", &sort_key, "sort-key", + "key for sorting: sample(sort by samples number)" + " time (sort by avg time)"), + OPT_END() +}; + +static int kvm_events_report(int argc, const char **argv) +{ + symbol__init(); + + if (argc) { + argc = parse_options(argc, argv, + kvm_events_report_options, + kvm_events_report_usage, 0); + if (argc) + usage_with_options(kvm_events_report_usage, + kvm_events_report_options); + } + + return kvm_events_report_vcpu(trace_vcpu); +} + +static void print_kvm_stat_usage(void) +{ + printf("Usage: perf kvm stat <command>\n\n"); + + printf("# Available commands:\n"); + printf("\trecord: record kvm events\n"); + printf("\treport: report statistical data of kvm events\n"); + + printf("\nOtherwise, it is the alias of 'perf stat':\n"); +} + +static int kvm_cmd_stat(int argc, const char **argv) +{ + if (argc == 1) { + print_kvm_stat_usage(); + goto perf_stat; + } + + if (!strncmp(argv[1], "rec", 3)) + return kvm_events_record(argc - 1, argv + 1); + + if (!strncmp(argv[1], "rep", 3)) + return kvm_events_report(argc - 1 , argv + 1); + +perf_stat: + return cmd_stat(argc, argv, NULL); +} + static char name_buffer[256]; static const char * const kvm_usage[] = { - "perf kvm [<options>] {top|record|report|diff|buildid-list}", + "perf kvm [<options>] {top|record|report|diff|buildid-list|stat}", NULL }; @@ -102,7 +930,7 @@ static int __cmd_buildid_list(int argc, const char **argv) return cmd_buildid_list(i, rec_argv, NULL); } -int cmd_kvm(int argc, const char **argv, const char *prefix __used) +int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) { perf_host = 0; perf_guest = 1; @@ -135,6 +963,8 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __used) return cmd_top(argc, argv, NULL); else if (!strncmp(argv[0], "buildid-list", 12)) return __cmd_buildid_list(argc, argv); + else if (!strncmp(argv[0], "stat", 4)) + return kvm_cmd_stat(argc, argv); else usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 6313b6eb3ebb..1948eceb517a 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -14,20 +14,20 @@ #include "util/parse-events.h" #include "util/cache.h" -int cmd_list(int argc, const char **argv, const char *prefix __used) +int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) { setup_pager(); if (argc == 1) - print_events(NULL); + print_events(NULL, false); else { int i; for (i = 1; i < argc; ++i) { - if (i > 1) + if (i > 2) putchar('\n'); if (strncmp(argv[i], "tracepoint", 10) == 0) - print_tracepoint_events(NULL, NULL); + print_tracepoint_events(NULL, NULL, false); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) print_events_type(PERF_TYPE_HARDWARE); @@ -36,13 +36,15 @@ int cmd_list(int argc, const char **argv, const char *prefix __used) print_events_type(PERF_TYPE_SOFTWARE); else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) - print_hwcache_events(NULL); + print_hwcache_events(NULL, false); + else if (strcmp(argv[i], "--raw-dump") == 0) + print_events(NULL, true); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; if (sep == NULL) { - print_events(argv[i]); + print_events(argv[i], false); continue; } sep_idx = sep - argv[i]; @@ -51,7 +53,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __used) return -1; s[sep_idx] = '\0'; - print_tracepoint_events(s, s + sep_idx + 1); + print_tracepoint_events(s, s + sep_idx + 1, false); free(s); } } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index b3c428548868..7d6e09949880 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1,6 +1,8 @@ #include "builtin.h" #include "perf.h" +#include "util/evlist.h" +#include "util/evsel.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" @@ -40,7 +42,7 @@ struct lock_stat { struct rb_node rb; /* used for sorting */ /* - * FIXME: raw_field_value() returns unsigned long long, + * FIXME: perf_evsel__intval() returns u64, * so address of lockdep_map should be dealed as 64bit. * Is there more better solution? */ @@ -160,8 +162,10 @@ static struct thread_stat *thread_stat_findnew_after_first(u32 tid) return st; st = zalloc(sizeof(struct thread_stat)); - if (!st) - die("memory allocation failed\n"); + if (!st) { + pr_err("memory allocation failed\n"); + return NULL; + } st->tid = tid; INIT_LIST_HEAD(&st->seq_list); @@ -180,8 +184,10 @@ static struct thread_stat *thread_stat_findnew_first(u32 tid) struct thread_stat *st; st = zalloc(sizeof(struct thread_stat)); - if (!st) - die("memory allocation failed\n"); + if (!st) { + pr_err("memory allocation failed\n"); + return NULL; + } st->tid = tid; INIT_LIST_HEAD(&st->seq_list); @@ -247,18 +253,20 @@ struct lock_key keys[] = { { NULL, NULL } }; -static void select_key(void) +static int select_key(void) { int i; for (i = 0; keys[i].name; i++) { if (!strcmp(keys[i].name, sort_key)) { compare = keys[i].key; - return; + return 0; } } - die("Unknown compare key:%s\n", sort_key); + pr_err("Unknown compare key: %s\n", sort_key); + + return -1; } static void insert_to_result(struct lock_stat *st, @@ -323,61 +331,24 @@ static struct lock_stat *lock_stat_findnew(void *addr, const char *name) return new; alloc_failed: - die("memory allocation failed\n"); + pr_err("memory allocation failed\n"); + return NULL; } static const char *input_name; -struct raw_event_sample { - u32 size; - char data[0]; -}; - -struct trace_acquire_event { - void *addr; - const char *name; - int flag; -}; - -struct trace_acquired_event { - void *addr; - const char *name; -}; +struct trace_lock_handler { + int (*acquire_event)(struct perf_evsel *evsel, + struct perf_sample *sample); -struct trace_contended_event { - void *addr; - const char *name; -}; + int (*acquired_event)(struct perf_evsel *evsel, + struct perf_sample *sample); -struct trace_release_event { - void *addr; - const char *name; -}; + int (*contended_event)(struct perf_evsel *evsel, + struct perf_sample *sample); -struct trace_lock_handler { - void (*acquire_event)(struct trace_acquire_event *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*acquired_event)(struct trace_acquired_event *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*contended_event)(struct trace_contended_event *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*release_event)(struct trace_release_event *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); + int (*release_event)(struct perf_evsel *evsel, + struct perf_sample *sample); }; static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr) @@ -390,8 +361,10 @@ static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr) } seq = zalloc(sizeof(struct lock_seq_stat)); - if (!seq) - die("Not enough memory\n"); + if (!seq) { + pr_err("memory allocation failed\n"); + return NULL; + } seq->state = SEQ_STATE_UNINITIALIZED; seq->addr = addr; @@ -414,33 +387,42 @@ enum acquire_flags { READ_LOCK = 2, }; -static void -report_lock_acquire_event(struct trace_acquire_event *acquire_event, - struct event_format *__event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int report_lock_acquire_event(struct perf_evsel *evsel, + struct perf_sample *sample) { + void *addr; struct lock_stat *ls; struct thread_stat *ts; struct lock_seq_stat *seq; + const char *name = perf_evsel__strval(evsel, sample, "name"); + u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr"); + int flag = perf_evsel__intval(evsel, sample, "flag"); + + memcpy(&addr, &tmp, sizeof(void *)); - ls = lock_stat_findnew(acquire_event->addr, acquire_event->name); + ls = lock_stat_findnew(addr, name); + if (!ls) + return -1; if (ls->discard) - return; + return 0; - ts = thread_stat_findnew(thread->pid); - seq = get_seq(ts, acquire_event->addr); + ts = thread_stat_findnew(sample->tid); + if (!ts) + return -1; + + seq = get_seq(ts, addr); + if (!seq) + return -1; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: case SEQ_STATE_RELEASED: - if (!acquire_event->flag) { + if (!flag) { seq->state = SEQ_STATE_ACQUIRING; } else { - if (acquire_event->flag & TRY_LOCK) + if (flag & TRY_LOCK) ls->nr_trylock++; - if (acquire_event->flag & READ_LOCK) + if (flag & READ_LOCK) ls->nr_readlock++; seq->state = SEQ_STATE_READ_ACQUIRED; seq->read_count = 1; @@ -448,7 +430,7 @@ report_lock_acquire_event(struct trace_acquire_event *acquire_event, } break; case SEQ_STATE_READ_ACQUIRED: - if (acquire_event->flag & READ_LOCK) { + if (flag & READ_LOCK) { seq->read_count++; ls->nr_acquired++; goto end; @@ -473,38 +455,46 @@ broken: } ls->nr_acquire++; - seq->prev_event_time = timestamp; + seq->prev_event_time = sample->time; end: - return; + return 0; } -static void -report_lock_acquired_event(struct trace_acquired_event *acquired_event, - struct event_format *__event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int report_lock_acquired_event(struct perf_evsel *evsel, + struct perf_sample *sample) { + void *addr; struct lock_stat *ls; struct thread_stat *ts; struct lock_seq_stat *seq; u64 contended_term; + const char *name = perf_evsel__strval(evsel, sample, "name"); + u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr"); + + memcpy(&addr, &tmp, sizeof(void *)); - ls = lock_stat_findnew(acquired_event->addr, acquired_event->name); + ls = lock_stat_findnew(addr, name); + if (!ls) + return -1; if (ls->discard) - return; + return 0; + + ts = thread_stat_findnew(sample->tid); + if (!ts) + return -1; - ts = thread_stat_findnew(thread->pid); - seq = get_seq(ts, acquired_event->addr); + seq = get_seq(ts, addr); + if (!seq) + return -1; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: /* orphan event, do nothing */ - return; + return 0; case SEQ_STATE_ACQUIRING: break; case SEQ_STATE_CONTENDED: - contended_term = timestamp - seq->prev_event_time; + contended_term = sample->time - seq->prev_event_time; ls->wait_time_total += contended_term; if (contended_term < ls->wait_time_min) ls->wait_time_min = contended_term; @@ -529,33 +519,41 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event, seq->state = SEQ_STATE_ACQUIRED; ls->nr_acquired++; - seq->prev_event_time = timestamp; + seq->prev_event_time = sample->time; end: - return; + return 0; } -static void -report_lock_contended_event(struct trace_contended_event *contended_event, - struct event_format *__event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int report_lock_contended_event(struct perf_evsel *evsel, + struct perf_sample *sample) { + void *addr; struct lock_stat *ls; struct thread_stat *ts; struct lock_seq_stat *seq; + const char *name = perf_evsel__strval(evsel, sample, "name"); + u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr"); - ls = lock_stat_findnew(contended_event->addr, contended_event->name); + memcpy(&addr, &tmp, sizeof(void *)); + + ls = lock_stat_findnew(addr, name); + if (!ls) + return -1; if (ls->discard) - return; + return 0; + + ts = thread_stat_findnew(sample->tid); + if (!ts) + return -1; - ts = thread_stat_findnew(thread->pid); - seq = get_seq(ts, contended_event->addr); + seq = get_seq(ts, addr); + if (!seq) + return -1; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: /* orphan event, do nothing */ - return; + return 0; case SEQ_STATE_ACQUIRING: break; case SEQ_STATE_RELEASED: @@ -576,28 +574,36 @@ report_lock_contended_event(struct trace_contended_event *contended_event, seq->state = SEQ_STATE_CONTENDED; ls->nr_contended++; - seq->prev_event_time = timestamp; + seq->prev_event_time = sample->time; end: - return; + return 0; } -static void -report_lock_release_event(struct trace_release_event *release_event, - struct event_format *__event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int report_lock_release_event(struct perf_evsel *evsel, + struct perf_sample *sample) { + void *addr; struct lock_stat *ls; struct thread_stat *ts; struct lock_seq_stat *seq; + const char *name = perf_evsel__strval(evsel, sample, "name"); + u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr"); + + memcpy(&addr, &tmp, sizeof(void *)); - ls = lock_stat_findnew(release_event->addr, release_event->name); + ls = lock_stat_findnew(addr, name); + if (!ls) + return -1; if (ls->discard) - return; + return 0; + + ts = thread_stat_findnew(sample->tid); + if (!ts) + return -1; - ts = thread_stat_findnew(thread->pid); - seq = get_seq(ts, release_event->addr); + seq = get_seq(ts, addr); + if (!seq) + return -1; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: @@ -631,7 +637,7 @@ free_seq: list_del(&seq->list); free(seq); end: - return; + return 0; } /* lock oriented handlers */ @@ -645,96 +651,36 @@ static struct trace_lock_handler report_lock_ops = { static struct trace_lock_handler *trace_handler; -static void -process_lock_acquire_event(void *data, - struct event_format *event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) -{ - struct trace_acquire_event acquire_event; - u64 tmp; /* this is required for casting... */ - - tmp = raw_field_value(event, "lockdep_addr", data); - memcpy(&acquire_event.addr, &tmp, sizeof(void *)); - acquire_event.name = (char *)raw_field_ptr(event, "name", data); - acquire_event.flag = (int)raw_field_value(event, "flag", data); - - if (trace_handler->acquire_event) - trace_handler->acquire_event(&acquire_event, event, cpu, timestamp, thread); -} - -static void -process_lock_acquired_event(void *data, - struct event_format *event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int perf_evsel__process_lock_acquire(struct perf_evsel *evsel, + struct perf_sample *sample) { - struct trace_acquired_event acquired_event; - u64 tmp; /* this is required for casting... */ - - tmp = raw_field_value(event, "lockdep_addr", data); - memcpy(&acquired_event.addr, &tmp, sizeof(void *)); - acquired_event.name = (char *)raw_field_ptr(event, "name", data); - if (trace_handler->acquire_event) - trace_handler->acquired_event(&acquired_event, event, cpu, timestamp, thread); + return trace_handler->acquire_event(evsel, sample); + return 0; } -static void -process_lock_contended_event(void *data, - struct event_format *event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int perf_evsel__process_lock_acquired(struct perf_evsel *evsel, + struct perf_sample *sample) { - struct trace_contended_event contended_event; - u64 tmp; /* this is required for casting... */ - - tmp = raw_field_value(event, "lockdep_addr", data); - memcpy(&contended_event.addr, &tmp, sizeof(void *)); - contended_event.name = (char *)raw_field_ptr(event, "name", data); - - if (trace_handler->acquire_event) - trace_handler->contended_event(&contended_event, event, cpu, timestamp, thread); + if (trace_handler->acquired_event) + return trace_handler->acquired_event(evsel, sample); + return 0; } -static void -process_lock_release_event(void *data, - struct event_format *event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int perf_evsel__process_lock_contended(struct perf_evsel *evsel, + struct perf_sample *sample) { - struct trace_release_event release_event; - u64 tmp; /* this is required for casting... */ - - tmp = raw_field_value(event, "lockdep_addr", data); - memcpy(&release_event.addr, &tmp, sizeof(void *)); - release_event.name = (char *)raw_field_ptr(event, "name", data); - - if (trace_handler->acquire_event) - trace_handler->release_event(&release_event, event, cpu, timestamp, thread); + if (trace_handler->contended_event) + return trace_handler->contended_event(evsel, sample); + return 0; } -static void -process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread) +static int perf_evsel__process_lock_release(struct perf_evsel *evsel, + struct perf_sample *sample) { - struct event_format *event; - int type; - - type = trace_parse_common_type(session->pevent, data); - event = pevent_find_event(session->pevent, type); - - if (!strcmp(event->name, "lock_acquire")) - process_lock_acquire_event(data, event, cpu, timestamp, thread); - if (!strcmp(event->name, "lock_acquired")) - process_lock_acquired_event(data, event, cpu, timestamp, thread); - if (!strcmp(event->name, "lock_contended")) - process_lock_contended_event(data, event, cpu, timestamp, thread); - if (!strcmp(event->name, "lock_release")) - process_lock_release_event(data, event, cpu, timestamp, thread); + if (trace_handler->release_event) + return trace_handler->release_event(evsel, sample); + return 0; } static void print_bad_events(int bad, int total) @@ -836,20 +782,29 @@ static void dump_map(void) } } -static void dump_info(void) +static int dump_info(void) { + int rc = 0; + if (info_threads) dump_threads(); else if (info_map) dump_map(); - else - die("Unknown type of information\n"); + else { + rc = -1; + pr_err("Unknown type of information\n"); + } + + return rc; } -static int process_sample_event(struct perf_tool *tool __used, +typedef int (*tracepoint_handler)(struct perf_evsel *evsel, + struct perf_sample *sample); + +static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __used, + struct perf_evsel *evsel, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, sample->tid); @@ -860,7 +815,10 @@ static int process_sample_event(struct perf_tool *tool __used, return -1; } - process_raw_event(sample->raw_data, sample->cpu, sample->time, thread); + if (evsel->handler.func != NULL) { + tracepoint_handler f = evsel->handler.func; + return f(evsel, sample); + } return 0; } @@ -871,11 +829,25 @@ static struct perf_tool eops = { .ordered_samples = true, }; +static const struct perf_evsel_str_handler lock_tracepoints[] = { + { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */ + { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ + { "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ + { "lock:lock_release", perf_evsel__process_lock_release, }, /* CONFIG_LOCKDEP */ +}; + static int read_events(void) { session = perf_session__new(input_name, O_RDONLY, 0, false, &eops); - if (!session) - die("Initializing perf session failed\n"); + if (!session) { + pr_err("Initializing perf session failed\n"); + return -1; + } + + if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) { + pr_err("Initializing perf session tracepoint handlers failed\n"); + return -1; + } return perf_session__process_events(session, &eops); } @@ -892,13 +864,18 @@ static void sort_result(void) } } -static void __cmd_report(void) +static int __cmd_report(void) { setup_pager(); - select_key(); - read_events(); + + if ((select_key() != 0) || + (read_events() != 0)) + return -1; + sort_result(); print_result(); + + return 0; } static const char * const report_usage[] = { @@ -944,10 +921,6 @@ static const char *record_args[] = { "-f", "-m", "1024", "-c", "1", - "-e", "lock:lock_acquire", - "-e", "lock:lock_acquired", - "-e", "lock:lock_contended", - "-e", "lock:lock_release", }; static int __cmd_record(int argc, const char **argv) @@ -955,15 +928,31 @@ static int __cmd_record(int argc, const char **argv) unsigned int rec_argc, i, j; const char **rec_argv; + for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) { + if (!is_valid_tracepoint(lock_tracepoints[i].name)) { + pr_err("tracepoint %s is not enabled. " + "Are CONFIG_LOCKDEP and CONFIG_LOCK_STAT enabled?\n", + lock_tracepoints[i].name); + return 1; + } + } + rec_argc = ARRAY_SIZE(record_args) + argc - 1; - rec_argv = calloc(rec_argc + 1, sizeof(char *)); + /* factor of 2 is for -e in front of each tracepoint */ + rec_argc += 2 * ARRAY_SIZE(lock_tracepoints); + rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = strdup(record_args[i]); + for (j = 0; j < ARRAY_SIZE(lock_tracepoints); j++) { + rec_argv[i++] = "-e"; + rec_argv[i++] = strdup(lock_tracepoints[j].name); + } + for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; @@ -972,9 +961,10 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -int cmd_lock(int argc, const char **argv, const char *prefix __used) +int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) { unsigned int i; + int rc = 0; symbol__init(); for (i = 0; i < LOCKHASH_SIZE; i++) @@ -1009,11 +999,13 @@ int cmd_lock(int argc, const char **argv, const char *prefix __used) /* recycling report_lock_ops */ trace_handler = &report_lock_ops; setup_pager(); - read_events(); - dump_info(); + if (read_events() != 0) + rc = -1; + else + rc = dump_info(); } else { usage_with_options(lock_usage, lock_options); } - return 0; + return rc; } diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index e215ae61b2ae..118aa8946573 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -143,8 +143,8 @@ static int parse_probe_event_argv(int argc, const char **argv) return ret; } -static int opt_add_probe_event(const struct option *opt __used, - const char *str, int unset __used) +static int opt_add_probe_event(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { if (str) { params.mod_events = true; @@ -153,8 +153,8 @@ static int opt_add_probe_event(const struct option *opt __used, return 0; } -static int opt_del_probe_event(const struct option *opt __used, - const char *str, int unset __used) +static int opt_del_probe_event(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { if (str) { params.mod_events = true; @@ -166,7 +166,7 @@ static int opt_del_probe_event(const struct option *opt __used, } static int opt_set_target(const struct option *opt, const char *str, - int unset __used) + int unset __maybe_unused) { int ret = -ENOENT; @@ -188,8 +188,8 @@ static int opt_set_target(const struct option *opt, const char *str, } #ifdef DWARF_SUPPORT -static int opt_show_lines(const struct option *opt __used, - const char *str, int unset __used) +static int opt_show_lines(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { int ret = 0; @@ -209,8 +209,8 @@ static int opt_show_lines(const struct option *opt __used, return ret; } -static int opt_show_vars(const struct option *opt __used, - const char *str, int unset __used) +static int opt_show_vars(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { struct perf_probe_event *pev = ¶ms.events[params.nevents]; int ret; @@ -229,8 +229,8 @@ static int opt_show_vars(const struct option *opt __used, } #endif -static int opt_set_filter(const struct option *opt __used, - const char *str, int unset __used) +static int opt_set_filter(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { const char *err; @@ -327,7 +327,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_probe(int argc, const char **argv, const char *prefix __used) +int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) { int ret; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4db6e1ba54e3..f14cb5fdb91f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -31,6 +31,15 @@ #include <sched.h> #include <sys/mman.h> +#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " + +#ifdef NO_LIBUNWIND_SUPPORT +static char callchain_help[] = CALLCHAIN_HELP "[fp]"; +#else +static unsigned long default_stack_dump_size = 8192; +static char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +#endif + enum write_mode_t { WRITE_FORCE, WRITE_APPEND @@ -62,32 +71,38 @@ static void advance_output(struct perf_record *rec, size_t size) rec->bytes_written += size; } -static void write_output(struct perf_record *rec, void *buf, size_t size) +static int write_output(struct perf_record *rec, void *buf, size_t size) { while (size) { int ret = write(rec->output, buf, size); - if (ret < 0) - die("failed to write"); + if (ret < 0) { + pr_err("failed to write\n"); + return -1; + } size -= ret; buf += ret; rec->bytes_written += ret; } + + return 0; } static int process_synthesized_event(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __used, - struct machine *machine __used) + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { struct perf_record *rec = container_of(tool, struct perf_record, tool); - write_output(rec, event, event->header.size); + if (write_output(rec, event, event->header.size) < 0) + return -1; + return 0; } -static void perf_record__mmap_read(struct perf_record *rec, +static int perf_record__mmap_read(struct perf_record *rec, struct perf_mmap *md) { unsigned int head = perf_mmap__read_head(md); @@ -95,9 +110,10 @@ static void perf_record__mmap_read(struct perf_record *rec, unsigned char *data = md->base + rec->page_size; unsigned long size; void *buf; + int rc = 0; if (old == head) - return; + return 0; rec->samples++; @@ -108,17 +124,26 @@ static void perf_record__mmap_read(struct perf_record *rec, size = md->mask + 1 - (old & md->mask); old += size; - write_output(rec, buf, size); + if (write_output(rec, buf, size) < 0) { + rc = -1; + goto out; + } } buf = &data[old & md->mask]; size = head - old; old += size; - write_output(rec, buf, size); + if (write_output(rec, buf, size) < 0) { + rc = -1; + goto out; + } md->prev = old; perf_mmap__write_tail(md, old); + +out: + return rc; } static volatile int done = 0; @@ -134,7 +159,7 @@ static void sig_handler(int sig) signr = sig; } -static void perf_record__sig_exit(int exit_status __used, void *arg) +static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg) { struct perf_record *rec = arg; int status; @@ -163,31 +188,32 @@ static bool perf_evlist__equal(struct perf_evlist *evlist, if (evlist->nr_entries != other->nr_entries) return false; - pair = list_entry(other->entries.next, struct perf_evsel, node); + pair = perf_evlist__first(other); list_for_each_entry(pos, &evlist->entries, node) { if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0)) return false; - pair = list_entry(pair->node.next, struct perf_evsel, node); + pair = perf_evsel__next(pair); } return true; } -static void perf_record__open(struct perf_record *rec) +static int perf_record__open(struct perf_record *rec) { - struct perf_evsel *pos, *first; + struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; struct perf_record_opts *opts = &rec->opts; - - first = list_entry(evlist->entries.next, struct perf_evsel, node); + int rc = 0; perf_evlist__config_attrs(evlist, opts); + if (opts->group) + perf_evlist__set_leader(evlist); + list_for_each_entry(pos, &evlist->entries, node) { struct perf_event_attr *attr = &pos->attr; - struct xyarray *group_fd = NULL; /* * Check if parse_single_tracepoint_event has already asked for * PERF_SAMPLE_TIME. @@ -202,24 +228,24 @@ static void perf_record__open(struct perf_record *rec) */ bool time_needed = attr->sample_type & PERF_SAMPLE_TIME; - if (opts->group && pos != first) - group_fd = first->fd; fallback_missing_features: if (opts->exclude_guest_missing) attr->exclude_guest = attr->exclude_host = 0; retry_sample_id: attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; try_again: - if (perf_evsel__open(pos, evlist->cpus, evlist->threads, - opts->group, group_fd) < 0) { + if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) { int err = errno; if (err == EPERM || err == EACCES) { ui__error_paranoid(); - exit(EXIT_FAILURE); + rc = -err; + goto out; } else if (err == ENODEV && opts->target.cpu_list) { - die("No such device - did you specify" - " an out-of-range profile CPU?\n"); + pr_err("No such device - did you specify" + " an out-of-range profile CPU?\n"); + rc = -err; + goto out; } else if (err == EINVAL) { if (!opts->exclude_guest_missing && (attr->exclude_guest || attr->exclude_host)) { @@ -266,42 +292,57 @@ try_again: if (err == ENOENT) { ui__error("The %s event is not supported.\n", perf_evsel__name(pos)); - exit(EXIT_FAILURE); + rc = -err; + goto out; } printf("\n"); - error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n", - err, strerror(err)); + error("sys_perf_event_open() syscall returned with %d " + "(%s) for event %s. /bin/dmesg may provide " + "additional information.\n", + err, strerror(err), perf_evsel__name(pos)); #if defined(__i386__) || defined(__x86_64__) - if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) - die("No hardware sampling interrupt available." - " No APIC? If so then you can boot the kernel" - " with the \"lapic\" boot parameter to" - " force-enable it.\n"); + if (attr->type == PERF_TYPE_HARDWARE && + err == EOPNOTSUPP) { + pr_err("No hardware sampling interrupt available." + " No APIC? If so then you can boot the kernel" + " with the \"lapic\" boot parameter to" + " force-enable it.\n"); + rc = -err; + goto out; + } #endif - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + pr_err("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); + rc = -err; + goto out; } } - if (perf_evlist__set_filters(evlist)) { + if (perf_evlist__apply_filters(evlist)) { error("failed to set filter with %d (%s)\n", errno, strerror(errno)); - exit(-1); + rc = -1; + goto out; } if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) { - if (errno == EPERM) - die("Permission error mapping pages.\n" - "Consider increasing " - "/proc/sys/kernel/perf_event_mlock_kb,\n" - "or try again with a smaller value of -m/--mmap_pages.\n" - "(current value: %d)\n", opts->mmap_pages); - else if (!is_power_of_2(opts->mmap_pages)) - die("--mmap_pages/-m value must be a power of two."); - - die("failed to mmap with %d (%s)\n", errno, strerror(errno)); + if (errno == EPERM) { + pr_err("Permission error mapping pages.\n" + "Consider increasing " + "/proc/sys/kernel/perf_event_mlock_kb,\n" + "or try again with a smaller value of -m/--mmap_pages.\n" + "(current value: %d)\n", opts->mmap_pages); + rc = -errno; + } else if (!is_power_of_2(opts->mmap_pages)) { + pr_err("--mmap_pages/-m value must be a power of two."); + rc = -EINVAL; + } else { + pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno)); + rc = -errno; + } + goto out; } if (rec->file_new) @@ -309,11 +350,14 @@ try_again: else { if (!perf_evlist__equal(session->evlist, evlist)) { fprintf(stderr, "incompatible append\n"); - exit(-1); + rc = -1; + goto out; } } perf_session__set_id_hdr_size(session); +out: + return rc; } static int process_buildids(struct perf_record *rec) @@ -329,10 +373,13 @@ static int process_buildids(struct perf_record *rec) size, &build_id__mark_dso_hit_ops); } -static void perf_record__exit(int status __used, void *arg) +static void perf_record__exit(int status, void *arg) { struct perf_record *rec = arg; + if (status != 0) + return; + if (!rec->opts.pipe_output) { rec->session->header.data_size += rec->bytes_written; @@ -387,17 +434,26 @@ static struct perf_event_header finished_round_event = { .type = PERF_RECORD_FINISHED_ROUND, }; -static void perf_record__mmap_read_all(struct perf_record *rec) +static int perf_record__mmap_read_all(struct perf_record *rec) { int i; + int rc = 0; for (i = 0; i < rec->evlist->nr_mmaps; i++) { - if (rec->evlist->mmap[i].base) - perf_record__mmap_read(rec, &rec->evlist->mmap[i]); + if (rec->evlist->mmap[i].base) { + if (perf_record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) { + rc = -1; + goto out; + } + } } if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA)) - write_output(rec, &finished_round_event, sizeof(finished_round_event)); + rc = write_output(rec, &finished_round_event, + sizeof(finished_round_event)); + +out: + return rc; } static int __cmd_record(struct perf_record *rec, int argc, const char **argv) @@ -457,7 +513,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) output = open(output_name, flags, S_IRUSR | S_IWUSR); if (output < 0) { perror("failed to create output file"); - exit(-1); + return -1; } rec->output = output; @@ -497,7 +553,10 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) } } - perf_record__open(rec); + if (perf_record__open(rec) != 0) { + err = -1; + goto out_delete_session; + } /* * perf_session__delete(session) will be called at perf_record__exit() @@ -507,19 +566,20 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) if (opts->pipe_output) { err = perf_header__write_pipe(output); if (err < 0) - return err; + goto out_delete_session; } else if (rec->file_new) { err = perf_session__write_header(session, evsel_list, output, false); if (err < 0) - return err; + goto out_delete_session; } if (!rec->no_buildid && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) { pr_err("Couldn't generate buildids. " "Use --no-buildid to profile anyway.\n"); - return -1; + err = -1; + goto out_delete_session; } rec->post_processing_offset = lseek(output, 0, SEEK_CUR); @@ -527,7 +587,8 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) machine = perf_session__find_host_machine(session); if (!machine) { pr_err("Couldn't find native kernel information.\n"); - return -1; + err = -1; + goto out_delete_session; } if (opts->pipe_output) { @@ -535,14 +596,14 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) process_synthesized_event); if (err < 0) { pr_err("Couldn't synthesize attrs.\n"); - return err; + goto out_delete_session; } err = perf_event__synthesize_event_types(tool, process_synthesized_event, machine); if (err < 0) { pr_err("Couldn't synthesize event_types.\n"); - return err; + goto out_delete_session; } if (have_tracepoints(&evsel_list->entries)) { @@ -558,7 +619,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) process_synthesized_event); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); - return err; + goto out_delete_session; } advance_output(rec, err); } @@ -586,20 +647,24 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) perf_event__synthesize_guest_os); if (!opts->target.system_wide) - perf_event__synthesize_thread_map(tool, evsel_list->threads, + err = perf_event__synthesize_thread_map(tool, evsel_list->threads, process_synthesized_event, machine); else - perf_event__synthesize_threads(tool, process_synthesized_event, + err = perf_event__synthesize_threads(tool, process_synthesized_event, machine); + if (err != 0) + goto out_delete_session; + if (rec->realtime_prio) { struct sched_param param; param.sched_priority = rec->realtime_prio; if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { pr_err("Could not set realtime priority.\n"); - exit(-1); + err = -1; + goto out_delete_session; } } @@ -614,7 +679,10 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) for (;;) { int hits = rec->samples; - perf_record__mmap_read_all(rec); + if (perf_record__mmap_read_all(rec) < 0) { + err = -1; + goto out_delete_session; + } if (hits == rec->samples) { if (done) @@ -732,6 +800,106 @@ error: return ret; } +#ifndef NO_LIBUNWIND_SUPPORT +static int get_stack_size(char *str, unsigned long *_size) +{ + char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); + + size = strtoul(str, &endptr, 0); + + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; + return 0; + + } while (0); + + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); + return -1; +} +#endif /* !NO_LIBUNWIND_SUPPORT */ + +static int +parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, + int unset) +{ + struct perf_record *rec = (struct perf_record *)opt->value; + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* --no-call-graph */ + if (unset) + return 0; + + /* We specified default option if none is provided. */ + BUG_ON(!arg); + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + rec->opts.call_graph = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for -g fp\n"); + break; + +#ifndef NO_LIBUNWIND_SUPPORT + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + ret = 0; + rec->opts.call_graph = CALLCHAIN_DWARF; + rec->opts.stack_dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; + + ret = get_stack_size(tok, &size); + rec->opts.stack_dump_size = size; + } + + if (!ret) + pr_debug("callchain: stack dump size %d\n", + rec->opts.stack_dump_size); +#endif /* !NO_LIBUNWIND_SUPPORT */ + } else { + pr_err("callchain: Unknown -g option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + + if (!ret) + pr_debug("callchain: type %d\n", rec->opts.call_graph); + + return ret; +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -803,8 +971,9 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_BOOLEAN('g', "call-graph", &record.opts.call_graph, - "do call-graph (stack chain/backtrace) recording"), + OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]", + callchain_help, &parse_callchain_opt, + "fp"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), @@ -836,7 +1005,7 @@ const struct option record_options[] = { OPT_END() }; -int cmd_record(int argc, const char **argv, const char *prefix __used) +int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) { int err = -ENOMEM; struct perf_evsel *pos; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 7c88a243b5db..1da243dfbc3e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -69,8 +69,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, al->thread, - sample->callchain, &parent); + err = machine__resolve_callchain(machine, evsel, al->thread, + sample, &parent); if (err) return err; } @@ -93,7 +93,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, struct annotation *notes; err = -ENOMEM; bx = he->branch_info; - if (bx->from.sym && use_browser > 0) { + if (bx->from.sym && use_browser == 1 && sort__has_sym) { notes = symbol__annotation(bx->from.sym); if (!notes->src && symbol__alloc_hist(bx->from.sym) < 0) @@ -107,7 +107,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, goto out; } - if (bx->to.sym && use_browser > 0) { + if (bx->to.sym && use_browser == 1 && sort__has_sym) { notes = symbol__annotation(bx->to.sym); if (!notes->src && symbol__alloc_hist(bx->to.sym) < 0) @@ -140,8 +140,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct hist_entry *he; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, al->thread, - sample->callchain, &parent); + err = machine__resolve_callchain(machine, evsel, al->thread, + sample, &parent); if (err) return err; } @@ -162,7 +162,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, * so we don't allocated the extra space needed because the stdio * code will not use it. */ - if (he->ms.sym != NULL && use_browser > 0) { + if (he->ms.sym != NULL && use_browser == 1 && sort__has_sym) { struct annotation *notes = symbol__annotation(he->ms.sym); assert(evsel != NULL); @@ -223,9 +223,9 @@ static int process_sample_event(struct perf_tool *tool, static int process_read_event(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample __maybe_unused, struct perf_evsel *evsel, - struct machine *machine __used) + struct machine *machine __maybe_unused) { struct perf_report *rep = container_of(tool, struct perf_report, tool); @@ -287,7 +287,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep) extern volatile int session_done; -static void sig_handler(int sig __used) +static void sig_handler(int sig __maybe_unused) { session_done = 1; } @@ -397,17 +397,17 @@ static int __cmd_report(struct perf_report *rep) desc); } - if (dump_trace) { - perf_session__fprintf_nr_events(session, stdout); - goto out_delete; - } - if (verbose > 3) perf_session__fprintf(session, stdout); if (verbose > 2) perf_session__fprintf_dsos(session, stdout); + if (dump_trace) { + perf_session__fprintf_nr_events(session, stdout); + goto out_delete; + } + nr_samples = 0; list_for_each_entry(pos, &session->evlist->entries, node) { struct hists *hists = &pos->hists; @@ -533,13 +533,14 @@ setup: } static int -parse_branch_mode(const struct option *opt __used, const char *str __used, int unset) +parse_branch_mode(const struct option *opt __maybe_unused, + const char *str __maybe_unused, int unset) { sort__branch_mode = !unset; return 0; } -int cmd_report(int argc, const char **argv, const char *prefix __used) +int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_session *session; struct stat st; @@ -638,6 +639,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) "Show a column with the sum of periods"), OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "", "use branch records for histogram filling", parse_branch_mode), + OPT_STRING(0, "objdump", &objdump_path, "path", + "objdump binary to use for disassembly and annotations"), OPT_END() }; @@ -686,15 +689,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) if (strcmp(report.input_name, "-") != 0) setup_browser(true); - else + else { use_browser = 0; + perf_hpp__init(false, false); + } + + setup_sorting(report_usage, options); /* * Only in the newt browser we are doing integrated annotation, * so don't allocate extra space that won't be used in the stdio * implementation. */ - if (use_browser > 0) { + if (use_browser == 1 && sort__has_sym) { symbol_conf.priv_size = sizeof(struct annotation); report.annotate_init = symbol__annotate_init; /* @@ -717,8 +724,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) if (symbol__init() < 0) goto error; - setup_sorting(report_usage, options); - if (parent_pattern != default_parent_pattern) { if (sort_dimension__add("parent") < 0) goto error; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 7a9ad2b1ee76..9b9e32eaa805 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -23,31 +23,12 @@ #include <pthread.h> #include <math.h> -static const char *input_name; - -static char default_sort_order[] = "avg, max, switch, runtime"; -static const char *sort_order = default_sort_order; - -static int profile_cpu = -1; - #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 - -static u64 run_measurement_overhead; -static u64 sleep_measurement_overhead; - #define COMM_LEN 20 #define SYM_LEN 129 - #define MAX_PID 65536 -static unsigned long nr_tasks; - -struct perf_sched { - struct perf_tool tool; - struct perf_session *session; -}; - struct sched_atom; struct task_desc { @@ -85,44 +66,6 @@ struct sched_atom { struct task_desc *wakee; }; -static struct task_desc *pid_to_task[MAX_PID]; - -static struct task_desc **tasks; - -static pthread_mutex_t start_work_mutex = PTHREAD_MUTEX_INITIALIZER; -static u64 start_time; - -static pthread_mutex_t work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER; - -static unsigned long nr_run_events; -static unsigned long nr_sleep_events; -static unsigned long nr_wakeup_events; - -static unsigned long nr_sleep_corrections; -static unsigned long nr_run_events_optimized; - -static unsigned long targetless_wakeups; -static unsigned long multitarget_wakeups; - -static u64 cpu_usage; -static u64 runavg_cpu_usage; -static u64 parent_cpu_usage; -static u64 runavg_parent_cpu_usage; - -static unsigned long nr_runs; -static u64 sum_runtime; -static u64 sum_fluct; -static u64 run_avg; - -static unsigned int replay_repeat = 10; -static unsigned long nr_timestamps; -static unsigned long nr_unordered_timestamps; -static unsigned long nr_state_machine_bugs; -static unsigned long nr_context_switch_bugs; -static unsigned long nr_events; -static unsigned long nr_lost_chunks; -static unsigned long nr_lost_events; - #define TASK_STATE_TO_CHAR_STR "RSDTtZX" enum thread_state { @@ -154,11 +97,79 @@ struct work_atoms { typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *); -static struct rb_root atom_root, sorted_atom_root; +struct perf_sched; + +struct trace_sched_handler { + int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample, struct machine *machine); -static u64 all_runtime; -static u64 all_count; + int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample, struct machine *machine); + int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample, struct machine *machine); + + int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample); + + int (*migrate_task_event)(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine); +}; + +struct perf_sched { + struct perf_tool tool; + const char *input_name; + const char *sort_order; + unsigned long nr_tasks; + struct task_desc *pid_to_task[MAX_PID]; + struct task_desc **tasks; + const struct trace_sched_handler *tp_handler; + pthread_mutex_t start_work_mutex; + pthread_mutex_t work_done_wait_mutex; + int profile_cpu; +/* + * Track the current task - that way we can know whether there's any + * weird events, such as a task being switched away that is not current. + */ + int max_cpu; + u32 curr_pid[MAX_CPUS]; + struct thread *curr_thread[MAX_CPUS]; + char next_shortname1; + char next_shortname2; + unsigned int replay_repeat; + unsigned long nr_run_events; + unsigned long nr_sleep_events; + unsigned long nr_wakeup_events; + unsigned long nr_sleep_corrections; + unsigned long nr_run_events_optimized; + unsigned long targetless_wakeups; + unsigned long multitarget_wakeups; + unsigned long nr_runs; + unsigned long nr_timestamps; + unsigned long nr_unordered_timestamps; + unsigned long nr_state_machine_bugs; + unsigned long nr_context_switch_bugs; + unsigned long nr_events; + unsigned long nr_lost_chunks; + unsigned long nr_lost_events; + u64 run_measurement_overhead; + u64 sleep_measurement_overhead; + u64 start_time; + u64 cpu_usage; + u64 runavg_cpu_usage; + u64 parent_cpu_usage; + u64 runavg_parent_cpu_usage; + u64 sum_runtime; + u64 sum_fluct; + u64 run_avg; + u64 all_runtime; + u64 all_count; + u64 cpu_last_switched[MAX_CPUS]; + struct rb_root atom_root, sorted_atom_root; + struct list_head sort_list, cmp_pid; +}; static u64 get_nsecs(void) { @@ -169,13 +180,13 @@ static u64 get_nsecs(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } -static void burn_nsecs(u64 nsecs) +static void burn_nsecs(struct perf_sched *sched, u64 nsecs) { u64 T0 = get_nsecs(), T1; do { T1 = get_nsecs(); - } while (T1 + run_measurement_overhead < T0 + nsecs); + } while (T1 + sched->run_measurement_overhead < T0 + nsecs); } static void sleep_nsecs(u64 nsecs) @@ -188,24 +199,24 @@ static void sleep_nsecs(u64 nsecs) nanosleep(&ts, NULL); } -static void calibrate_run_measurement_overhead(void) +static void calibrate_run_measurement_overhead(struct perf_sched *sched) { u64 T0, T1, delta, min_delta = 1000000000ULL; int i; for (i = 0; i < 10; i++) { T0 = get_nsecs(); - burn_nsecs(0); + burn_nsecs(sched, 0); T1 = get_nsecs(); delta = T1-T0; min_delta = min(min_delta, delta); } - run_measurement_overhead = min_delta; + sched->run_measurement_overhead = min_delta; printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta); } -static void calibrate_sleep_measurement_overhead(void) +static void calibrate_sleep_measurement_overhead(struct perf_sched *sched) { u64 T0, T1, delta, min_delta = 1000000000ULL; int i; @@ -218,7 +229,7 @@ static void calibrate_sleep_measurement_overhead(void) min_delta = min(min_delta, delta); } min_delta -= 10000; - sleep_measurement_overhead = min_delta; + sched->sleep_measurement_overhead = min_delta; printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta); } @@ -251,8 +262,8 @@ static struct sched_atom *last_event(struct task_desc *task) return task->atoms[task->nr_events - 1]; } -static void -add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration) +static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task, + u64 timestamp, u64 duration) { struct sched_atom *event, *curr_event = last_event(task); @@ -261,7 +272,7 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration) * to it: */ if (curr_event && curr_event->type == SCHED_EVENT_RUN) { - nr_run_events_optimized++; + sched->nr_run_events_optimized++; curr_event->duration += duration; return; } @@ -271,12 +282,11 @@ add_sched_event_run(struct task_desc *task, u64 timestamp, u64 duration) event->type = SCHED_EVENT_RUN; event->duration = duration; - nr_run_events++; + sched->nr_run_events++; } -static void -add_sched_event_wakeup(struct task_desc *task, u64 timestamp, - struct task_desc *wakee) +static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *task, + u64 timestamp, struct task_desc *wakee) { struct sched_atom *event, *wakee_event; @@ -286,11 +296,11 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp, wakee_event = last_event(wakee); if (!wakee_event || wakee_event->type != SCHED_EVENT_SLEEP) { - targetless_wakeups++; + sched->targetless_wakeups++; return; } if (wakee_event->wait_sem) { - multitarget_wakeups++; + sched->multitarget_wakeups++; return; } @@ -299,89 +309,89 @@ add_sched_event_wakeup(struct task_desc *task, u64 timestamp, wakee_event->specific_wait = 1; event->wait_sem = wakee_event->wait_sem; - nr_wakeup_events++; + sched->nr_wakeup_events++; } -static void -add_sched_event_sleep(struct task_desc *task, u64 timestamp, - u64 task_state __used) +static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task, + u64 timestamp, u64 task_state __maybe_unused) { struct sched_atom *event = get_new_event(task, timestamp); event->type = SCHED_EVENT_SLEEP; - nr_sleep_events++; + sched->nr_sleep_events++; } -static struct task_desc *register_pid(unsigned long pid, const char *comm) +static struct task_desc *register_pid(struct perf_sched *sched, + unsigned long pid, const char *comm) { struct task_desc *task; BUG_ON(pid >= MAX_PID); - task = pid_to_task[pid]; + task = sched->pid_to_task[pid]; if (task) return task; task = zalloc(sizeof(*task)); task->pid = pid; - task->nr = nr_tasks; + task->nr = sched->nr_tasks; strcpy(task->comm, comm); /* * every task starts in sleeping state - this gets ignored * if there's no wakeup pointing to this sleep state: */ - add_sched_event_sleep(task, 0, 0); + add_sched_event_sleep(sched, task, 0, 0); - pid_to_task[pid] = task; - nr_tasks++; - tasks = realloc(tasks, nr_tasks*sizeof(struct task_task *)); - BUG_ON(!tasks); - tasks[task->nr] = task; + sched->pid_to_task[pid] = task; + sched->nr_tasks++; + sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *)); + BUG_ON(!sched->tasks); + sched->tasks[task->nr] = task; if (verbose) - printf("registered task #%ld, PID %ld (%s)\n", nr_tasks, pid, comm); + printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm); return task; } -static void print_task_traces(void) +static void print_task_traces(struct perf_sched *sched) { struct task_desc *task; unsigned long i; - for (i = 0; i < nr_tasks; i++) { - task = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + task = sched->tasks[i]; printf("task %6ld (%20s:%10ld), nr_events: %ld\n", task->nr, task->comm, task->pid, task->nr_events); } } -static void add_cross_task_wakeups(void) +static void add_cross_task_wakeups(struct perf_sched *sched) { struct task_desc *task1, *task2; unsigned long i, j; - for (i = 0; i < nr_tasks; i++) { - task1 = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + task1 = sched->tasks[i]; j = i + 1; - if (j == nr_tasks) + if (j == sched->nr_tasks) j = 0; - task2 = tasks[j]; - add_sched_event_wakeup(task1, 0, task2); + task2 = sched->tasks[j]; + add_sched_event_wakeup(sched, task1, 0, task2); } } -static void -process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom) +static void perf_sched__process_event(struct perf_sched *sched, + struct sched_atom *atom) { int ret = 0; switch (atom->type) { case SCHED_EVENT_RUN: - burn_nsecs(atom->duration); + burn_nsecs(sched, atom->duration); break; case SCHED_EVENT_SLEEP: if (atom->wait_sem) @@ -428,8 +438,8 @@ static int self_open_counters(void) fd = sys_perf_event_open(&attr, 0, -1, -1, 0); if (fd < 0) - die("Error: sys_perf_event_open() syscall returned" - "with %d (%s)\n", fd, strerror(errno)); + pr_err("Error: sys_perf_event_open() syscall returned " + "with %d (%s)\n", fd, strerror(errno)); return fd; } @@ -444,31 +454,41 @@ static u64 get_cpu_usage_nsec_self(int fd) return runtime; } +struct sched_thread_parms { + struct task_desc *task; + struct perf_sched *sched; +}; + static void *thread_func(void *ctx) { - struct task_desc *this_task = ctx; + struct sched_thread_parms *parms = ctx; + struct task_desc *this_task = parms->task; + struct perf_sched *sched = parms->sched; u64 cpu_usage_0, cpu_usage_1; unsigned long i, ret; char comm2[22]; int fd; + free(parms); + sprintf(comm2, ":%s", this_task->comm); prctl(PR_SET_NAME, comm2); fd = self_open_counters(); - + if (fd < 0) + return NULL; again: ret = sem_post(&this_task->ready_for_work); BUG_ON(ret); - ret = pthread_mutex_lock(&start_work_mutex); + ret = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(ret); - ret = pthread_mutex_unlock(&start_work_mutex); + ret = pthread_mutex_unlock(&sched->start_work_mutex); BUG_ON(ret); cpu_usage_0 = get_cpu_usage_nsec_self(fd); for (i = 0; i < this_task->nr_events; i++) { this_task->curr_event = i; - process_sched_event(this_task, this_task->atoms[i]); + perf_sched__process_event(sched, this_task->atoms[i]); } cpu_usage_1 = get_cpu_usage_nsec_self(fd); @@ -476,15 +496,15 @@ again: ret = sem_post(&this_task->work_done_sem); BUG_ON(ret); - ret = pthread_mutex_lock(&work_done_wait_mutex); + ret = pthread_mutex_lock(&sched->work_done_wait_mutex); BUG_ON(ret); - ret = pthread_mutex_unlock(&work_done_wait_mutex); + ret = pthread_mutex_unlock(&sched->work_done_wait_mutex); BUG_ON(ret); goto again; } -static void create_tasks(void) +static void create_tasks(struct perf_sched *sched) { struct task_desc *task; pthread_attr_t attr; @@ -496,128 +516,129 @@ static void create_tasks(void) err = pthread_attr_setstacksize(&attr, (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); BUG_ON(err); - err = pthread_mutex_lock(&start_work_mutex); + err = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(err); - err = pthread_mutex_lock(&work_done_wait_mutex); + err = pthread_mutex_lock(&sched->work_done_wait_mutex); BUG_ON(err); - for (i = 0; i < nr_tasks; i++) { - task = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + struct sched_thread_parms *parms = malloc(sizeof(*parms)); + BUG_ON(parms == NULL); + parms->task = task = sched->tasks[i]; + parms->sched = sched; sem_init(&task->sleep_sem, 0, 0); sem_init(&task->ready_for_work, 0, 0); sem_init(&task->work_done_sem, 0, 0); task->curr_event = 0; - err = pthread_create(&task->thread, &attr, thread_func, task); + err = pthread_create(&task->thread, &attr, thread_func, parms); BUG_ON(err); } } -static void wait_for_tasks(void) +static void wait_for_tasks(struct perf_sched *sched) { u64 cpu_usage_0, cpu_usage_1; struct task_desc *task; unsigned long i, ret; - start_time = get_nsecs(); - cpu_usage = 0; - pthread_mutex_unlock(&work_done_wait_mutex); + sched->start_time = get_nsecs(); + sched->cpu_usage = 0; + pthread_mutex_unlock(&sched->work_done_wait_mutex); - for (i = 0; i < nr_tasks; i++) { - task = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + task = sched->tasks[i]; ret = sem_wait(&task->ready_for_work); BUG_ON(ret); sem_init(&task->ready_for_work, 0, 0); } - ret = pthread_mutex_lock(&work_done_wait_mutex); + ret = pthread_mutex_lock(&sched->work_done_wait_mutex); BUG_ON(ret); cpu_usage_0 = get_cpu_usage_nsec_parent(); - pthread_mutex_unlock(&start_work_mutex); + pthread_mutex_unlock(&sched->start_work_mutex); - for (i = 0; i < nr_tasks; i++) { - task = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + task = sched->tasks[i]; ret = sem_wait(&task->work_done_sem); BUG_ON(ret); sem_init(&task->work_done_sem, 0, 0); - cpu_usage += task->cpu_usage; + sched->cpu_usage += task->cpu_usage; task->cpu_usage = 0; } cpu_usage_1 = get_cpu_usage_nsec_parent(); - if (!runavg_cpu_usage) - runavg_cpu_usage = cpu_usage; - runavg_cpu_usage = (runavg_cpu_usage*9 + cpu_usage)/10; + if (!sched->runavg_cpu_usage) + sched->runavg_cpu_usage = sched->cpu_usage; + sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10; - parent_cpu_usage = cpu_usage_1 - cpu_usage_0; - if (!runavg_parent_cpu_usage) - runavg_parent_cpu_usage = parent_cpu_usage; - runavg_parent_cpu_usage = (runavg_parent_cpu_usage*9 + - parent_cpu_usage)/10; + sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0; + if (!sched->runavg_parent_cpu_usage) + sched->runavg_parent_cpu_usage = sched->parent_cpu_usage; + sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 + + sched->parent_cpu_usage)/10; - ret = pthread_mutex_lock(&start_work_mutex); + ret = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(ret); - for (i = 0; i < nr_tasks; i++) { - task = tasks[i]; + for (i = 0; i < sched->nr_tasks; i++) { + task = sched->tasks[i]; sem_init(&task->sleep_sem, 0, 0); task->curr_event = 0; } } -static void run_one_test(void) +static void run_one_test(struct perf_sched *sched) { u64 T0, T1, delta, avg_delta, fluct; T0 = get_nsecs(); - wait_for_tasks(); + wait_for_tasks(sched); T1 = get_nsecs(); delta = T1 - T0; - sum_runtime += delta; - nr_runs++; + sched->sum_runtime += delta; + sched->nr_runs++; - avg_delta = sum_runtime / nr_runs; + avg_delta = sched->sum_runtime / sched->nr_runs; if (delta < avg_delta) fluct = avg_delta - delta; else fluct = delta - avg_delta; - sum_fluct += fluct; - if (!run_avg) - run_avg = delta; - run_avg = (run_avg*9 + delta)/10; + sched->sum_fluct += fluct; + if (!sched->run_avg) + sched->run_avg = delta; + sched->run_avg = (sched->run_avg * 9 + delta) / 10; - printf("#%-3ld: %0.3f, ", - nr_runs, (double)delta/1000000.0); + printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0); - printf("ravg: %0.2f, ", - (double)run_avg/1e6); + printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6); printf("cpu: %0.2f / %0.2f", - (double)cpu_usage/1e6, (double)runavg_cpu_usage/1e6); + (double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6); #if 0 /* * rusage statistics done by the parent, these are less - * accurate than the sum_exec_runtime based statistics: + * accurate than the sched->sum_exec_runtime based statistics: */ printf(" [%0.2f / %0.2f]", - (double)parent_cpu_usage/1e6, - (double)runavg_parent_cpu_usage/1e6); + (double)sched->parent_cpu_usage/1e6, + (double)sched->runavg_parent_cpu_usage/1e6); #endif printf("\n"); - if (nr_sleep_corrections) - printf(" (%ld sleep corrections)\n", nr_sleep_corrections); - nr_sleep_corrections = 0; + if (sched->nr_sleep_corrections) + printf(" (%ld sleep corrections)\n", sched->nr_sleep_corrections); + sched->nr_sleep_corrections = 0; } -static void test_calibrations(void) +static void test_calibrations(struct perf_sched *sched) { u64 T0, T1; T0 = get_nsecs(); - burn_nsecs(1e6); + burn_nsecs(sched, 1e6); T1 = get_nsecs(); printf("the run test took %" PRIu64 " nsecs\n", T1 - T0); @@ -629,236 +650,92 @@ static void test_calibrations(void) printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0); } -#define FILL_FIELD(ptr, field, event, data) \ - ptr.field = (typeof(ptr.field)) raw_field_value(event, #field, data) - -#define FILL_ARRAY(ptr, array, event, data) \ -do { \ - void *__array = raw_field_ptr(event, #array, data); \ - memcpy(ptr.array, __array, sizeof(ptr.array)); \ -} while(0) - -#define FILL_COMMON_FIELDS(ptr, event, data) \ -do { \ - FILL_FIELD(ptr, common_type, event, data); \ - FILL_FIELD(ptr, common_flags, event, data); \ - FILL_FIELD(ptr, common_preempt_count, event, data); \ - FILL_FIELD(ptr, common_pid, event, data); \ - FILL_FIELD(ptr, common_tgid, event, data); \ -} while (0) - - - -struct trace_switch_event { - u32 size; - - u16 common_type; - u8 common_flags; - u8 common_preempt_count; - u32 common_pid; - u32 common_tgid; - - char prev_comm[16]; - u32 prev_pid; - u32 prev_prio; - u64 prev_state; - char next_comm[16]; - u32 next_pid; - u32 next_prio; -}; - -struct trace_runtime_event { - u32 size; - - u16 common_type; - u8 common_flags; - u8 common_preempt_count; - u32 common_pid; - u32 common_tgid; - - char comm[16]; - u32 pid; - u64 runtime; - u64 vruntime; -}; - -struct trace_wakeup_event { - u32 size; - - u16 common_type; - u8 common_flags; - u8 common_preempt_count; - u32 common_pid; - u32 common_tgid; - - char comm[16]; - u32 pid; - - u32 prio; - u32 success; - u32 cpu; -}; - -struct trace_fork_event { - u32 size; - - u16 common_type; - u8 common_flags; - u8 common_preempt_count; - u32 common_pid; - u32 common_tgid; - - char parent_comm[16]; - u32 parent_pid; - char child_comm[16]; - u32 child_pid; -}; - -struct trace_migrate_task_event { - u32 size; - - u16 common_type; - u8 common_flags; - u8 common_preempt_count; - u32 common_pid; - u32 common_tgid; - - char comm[16]; - u32 pid; - - u32 prio; - u32 cpu; -}; - -struct trace_sched_handler { - void (*switch_event)(struct trace_switch_event *, - struct machine *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*runtime_event)(struct trace_runtime_event *, - struct machine *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*wakeup_event)(struct trace_wakeup_event *, - struct machine *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*fork_event)(struct trace_fork_event *, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); - - void (*migrate_task_event)(struct trace_migrate_task_event *, - struct machine *machine, - struct event_format *, - int cpu, - u64 timestamp, - struct thread *thread); -}; - - -static void -replay_wakeup_event(struct trace_wakeup_event *wakeup_event, - struct machine *machine __used, - struct event_format *event, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int +replay_wakeup_event(struct perf_sched *sched, + struct perf_evsel *evsel, struct perf_sample *sample, + struct machine *machine __maybe_unused) { + const char *comm = perf_evsel__strval(evsel, sample, "comm"); + const u32 pid = perf_evsel__intval(evsel, sample, "pid"); struct task_desc *waker, *wakee; if (verbose) { - printf("sched_wakeup event %p\n", event); + printf("sched_wakeup event %p\n", evsel); - printf(" ... pid %d woke up %s/%d\n", - wakeup_event->common_pid, - wakeup_event->comm, - wakeup_event->pid); + printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid); } - waker = register_pid(wakeup_event->common_pid, "<unknown>"); - wakee = register_pid(wakeup_event->pid, wakeup_event->comm); + waker = register_pid(sched, sample->tid, "<unknown>"); + wakee = register_pid(sched, pid, comm); - add_sched_event_wakeup(waker, timestamp, wakee); + add_sched_event_wakeup(sched, waker, sample->time, wakee); + return 0; } -static u64 cpu_last_switched[MAX_CPUS]; - -static void -replay_switch_event(struct trace_switch_event *switch_event, - struct machine *machine __used, - struct event_format *event, - int cpu, - u64 timestamp, - struct thread *thread __used) +static int replay_switch_event(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine __maybe_unused) { - struct task_desc *prev, __used *next; - u64 timestamp0; + const char *prev_comm = perf_evsel__strval(evsel, sample, "prev_comm"), + *next_comm = perf_evsel__strval(evsel, sample, "next_comm"); + const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), + next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state"); + struct task_desc *prev, __maybe_unused *next; + u64 timestamp0, timestamp = sample->time; + int cpu = sample->cpu; s64 delta; if (verbose) - printf("sched_switch event %p\n", event); + printf("sched_switch event %p\n", evsel); if (cpu >= MAX_CPUS || cpu < 0) - return; + return 0; - timestamp0 = cpu_last_switched[cpu]; + timestamp0 = sched->cpu_last_switched[cpu]; if (timestamp0) delta = timestamp - timestamp0; else delta = 0; - if (delta < 0) - die("hm, delta: %" PRIu64 " < 0 ?\n", delta); - - if (verbose) { - printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n", - switch_event->prev_comm, switch_event->prev_pid, - switch_event->next_comm, switch_event->next_pid, - delta); + if (delta < 0) { + pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta); + return -1; } - prev = register_pid(switch_event->prev_pid, switch_event->prev_comm); - next = register_pid(switch_event->next_pid, switch_event->next_comm); + pr_debug(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n", + prev_comm, prev_pid, next_comm, next_pid, delta); - cpu_last_switched[cpu] = timestamp; + prev = register_pid(sched, prev_pid, prev_comm); + next = register_pid(sched, next_pid, next_comm); - add_sched_event_run(prev, timestamp, delta); - add_sched_event_sleep(prev, timestamp, switch_event->prev_state); -} + sched->cpu_last_switched[cpu] = timestamp; + add_sched_event_run(sched, prev, timestamp, delta); + add_sched_event_sleep(sched, prev, timestamp, prev_state); -static void -replay_fork_event(struct trace_fork_event *fork_event, - struct event_format *event, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) + return 0; +} + +static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample) { + const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"), + *child_comm = perf_evsel__strval(evsel, sample, "child_comm"); + const u32 parent_pid = perf_evsel__intval(evsel, sample, "parent_pid"), + child_pid = perf_evsel__intval(evsel, sample, "child_pid"); + if (verbose) { - printf("sched_fork event %p\n", event); - printf("... parent: %s/%d\n", fork_event->parent_comm, fork_event->parent_pid); - printf("... child: %s/%d\n", fork_event->child_comm, fork_event->child_pid); + printf("sched_fork event %p\n", evsel); + printf("... parent: %s/%d\n", parent_comm, parent_pid); + printf("... child: %s/%d\n", child_comm, child_pid); } - register_pid(fork_event->parent_pid, fork_event->parent_comm); - register_pid(fork_event->child_pid, fork_event->child_comm); -} -static struct trace_sched_handler replay_ops = { - .wakeup_event = replay_wakeup_event, - .switch_event = replay_switch_event, - .fork_event = replay_fork_event, -}; + register_pid(sched, parent_pid, parent_comm); + register_pid(sched, child_pid, child_comm); + return 0; +} struct sort_dimension { const char *name; @@ -866,8 +743,6 @@ struct sort_dimension { struct list_head list; }; -static LIST_HEAD(cmp_pid); - static int thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r) { @@ -936,43 +811,45 @@ __thread_latency_insert(struct rb_root *root, struct work_atoms *data, rb_insert_color(&data->node, root); } -static void thread_atoms_insert(struct thread *thread) +static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) { struct work_atoms *atoms = zalloc(sizeof(*atoms)); - if (!atoms) - die("No memory"); + if (!atoms) { + pr_err("No memory at %s\n", __func__); + return -1; + } atoms->thread = thread; INIT_LIST_HEAD(&atoms->work_list); - __thread_latency_insert(&atom_root, atoms, &cmp_pid); + __thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid); + return 0; } -static void -latency_fork_event(struct trace_fork_event *fork_event __used, - struct event_format *event __used, - int cpu __used, - u64 timestamp __used, - struct thread *thread __used) +static int latency_fork_event(struct perf_sched *sched __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused) { /* should insert the newcomer */ + return 0; } -__used -static char sched_out_state(struct trace_switch_event *switch_event) +static char sched_out_state(u64 prev_state) { const char *str = TASK_STATE_TO_CHAR_STR; - return str[switch_event->prev_state]; + return str[prev_state]; } -static void +static int add_sched_out_event(struct work_atoms *atoms, char run_state, u64 timestamp) { struct work_atom *atom = zalloc(sizeof(*atom)); - if (!atom) - die("Non memory"); + if (!atom) { + pr_err("Non memory at %s", __func__); + return -1; + } atom->sched_out_time = timestamp; @@ -982,10 +859,12 @@ add_sched_out_event(struct work_atoms *atoms, } list_add_tail(&atom->list, &atoms->work_list); + return 0; } static void -add_runtime_event(struct work_atoms *atoms, u64 delta, u64 timestamp __used) +add_runtime_event(struct work_atoms *atoms, u64 delta, + u64 timestamp __maybe_unused) { struct work_atom *atom; @@ -1028,106 +907,128 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) atoms->nb_atoms++; } -static void -latency_switch_event(struct trace_switch_event *switch_event, - struct machine *machine, - struct event_format *event __used, - int cpu, - u64 timestamp, - struct thread *thread __used) +static int latency_switch_event(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { + const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), + next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state"); struct work_atoms *out_events, *in_events; struct thread *sched_out, *sched_in; - u64 timestamp0; + u64 timestamp0, timestamp = sample->time; + int cpu = sample->cpu; s64 delta; BUG_ON(cpu >= MAX_CPUS || cpu < 0); - timestamp0 = cpu_last_switched[cpu]; - cpu_last_switched[cpu] = timestamp; + timestamp0 = sched->cpu_last_switched[cpu]; + sched->cpu_last_switched[cpu] = timestamp; if (timestamp0) delta = timestamp - timestamp0; else delta = 0; - if (delta < 0) - die("hm, delta: %" PRIu64 " < 0 ?\n", delta); - + if (delta < 0) { + pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta); + return -1; + } - sched_out = machine__findnew_thread(machine, switch_event->prev_pid); - sched_in = machine__findnew_thread(machine, switch_event->next_pid); + sched_out = machine__findnew_thread(machine, prev_pid); + sched_in = machine__findnew_thread(machine, next_pid); - out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid); + out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { - thread_atoms_insert(sched_out); - out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid); - if (!out_events) - die("out-event: Internal tree error"); + if (thread_atoms_insert(sched, sched_out)) + return -1; + out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); + if (!out_events) { + pr_err("out-event: Internal tree error"); + return -1; + } } - add_sched_out_event(out_events, sched_out_state(switch_event), timestamp); + if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp)) + return -1; - in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid); + in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); if (!in_events) { - thread_atoms_insert(sched_in); - in_events = thread_atoms_search(&atom_root, sched_in, &cmp_pid); - if (!in_events) - die("in-event: Internal tree error"); + if (thread_atoms_insert(sched, sched_in)) + return -1; + in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid); + if (!in_events) { + pr_err("in-event: Internal tree error"); + return -1; + } /* * Take came in we have not heard about yet, * add in an initial atom in runnable state: */ - add_sched_out_event(in_events, 'R', timestamp); + if (add_sched_out_event(in_events, 'R', timestamp)) + return -1; } add_sched_in_event(in_events, timestamp); + + return 0; } -static void -latency_runtime_event(struct trace_runtime_event *runtime_event, - struct machine *machine, - struct event_format *event __used, - int cpu, - u64 timestamp, - struct thread *this_thread __used) +static int latency_runtime_event(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, runtime_event->pid); - struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid); + const u32 pid = perf_evsel__intval(evsel, sample, "pid"); + const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); + struct thread *thread = machine__findnew_thread(machine, pid); + struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); + u64 timestamp = sample->time; + int cpu = sample->cpu; BUG_ON(cpu >= MAX_CPUS || cpu < 0); if (!atoms) { - thread_atoms_insert(thread); - atoms = thread_atoms_search(&atom_root, thread, &cmp_pid); - if (!atoms) - die("in-event: Internal tree error"); - add_sched_out_event(atoms, 'R', timestamp); + if (thread_atoms_insert(sched, thread)) + return -1; + atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); + if (!atoms) { + pr_err("in-event: Internal tree error"); + return -1; + } + if (add_sched_out_event(atoms, 'R', timestamp)) + return -1; } - add_runtime_event(atoms, runtime_event->runtime, timestamp); + add_runtime_event(atoms, runtime, timestamp); + return 0; } -static void -latency_wakeup_event(struct trace_wakeup_event *wakeup_event, - struct machine *machine, - struct event_format *__event __used, - int cpu __used, - u64 timestamp, - struct thread *thread __used) +static int latency_wakeup_event(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { + const u32 pid = perf_evsel__intval(evsel, sample, "pid"), + success = perf_evsel__intval(evsel, sample, "success"); struct work_atoms *atoms; struct work_atom *atom; struct thread *wakee; + u64 timestamp = sample->time; /* Note for later, it may be interesting to observe the failing cases */ - if (!wakeup_event->success) - return; + if (!success) + return 0; - wakee = machine__findnew_thread(machine, wakeup_event->pid); - atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid); + wakee = machine__findnew_thread(machine, pid); + atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { - thread_atoms_insert(wakee); - atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid); - if (!atoms) - die("wakeup-event: Internal tree error"); - add_sched_out_event(atoms, 'S', timestamp); + if (thread_atoms_insert(sched, wakee)) + return -1; + atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); + if (!atoms) { + pr_err("wakeup-event: Internal tree error"); + return -1; + } + if (add_sched_out_event(atoms, 'S', timestamp)) + return -1; } BUG_ON(list_empty(&atoms->work_list)); @@ -1139,27 +1040,27 @@ latency_wakeup_event(struct trace_wakeup_event *wakeup_event, * one CPU, or are only looking at only one, so don't * make useless noise. */ - if (profile_cpu == -1 && atom->state != THREAD_SLEEPING) - nr_state_machine_bugs++; + if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING) + sched->nr_state_machine_bugs++; - nr_timestamps++; + sched->nr_timestamps++; if (atom->sched_out_time > timestamp) { - nr_unordered_timestamps++; - return; + sched->nr_unordered_timestamps++; + return 0; } atom->state = THREAD_WAIT_CPU; atom->wake_up_time = timestamp; + return 0; } -static void -latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event, - struct machine *machine, - struct event_format *__event __used, - int cpu __used, - u64 timestamp, - struct thread *thread __used) +static int latency_migrate_task_event(struct perf_sched *sched, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { + const u32 pid = perf_evsel__intval(evsel, sample, "pid"); + u64 timestamp = sample->time; struct work_atoms *atoms; struct work_atom *atom; struct thread *migrant; @@ -1167,18 +1068,22 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event, /* * Only need to worry about migration when profiling one CPU. */ - if (profile_cpu == -1) - return; + if (sched->profile_cpu == -1) + return 0; - migrant = machine__findnew_thread(machine, migrate_task_event->pid); - atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid); + migrant = machine__findnew_thread(machine, pid); + atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { - thread_atoms_insert(migrant); - register_pid(migrant->pid, migrant->comm); - atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid); - if (!atoms) - die("migration-event: Internal tree error"); - add_sched_out_event(atoms, 'R', timestamp); + if (thread_atoms_insert(sched, migrant)) + return -1; + register_pid(sched, migrant->pid, migrant->comm); + atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); + if (!atoms) { + pr_err("migration-event: Internal tree error"); + return -1; + } + if (add_sched_out_event(atoms, 'R', timestamp)) + return -1; } BUG_ON(list_empty(&atoms->work_list)); @@ -1186,21 +1091,15 @@ latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event, atom = list_entry(atoms->work_list.prev, struct work_atom, list); atom->sched_in_time = atom->sched_out_time = atom->wake_up_time = timestamp; - nr_timestamps++; + sched->nr_timestamps++; if (atom->sched_out_time > timestamp) - nr_unordered_timestamps++; -} + sched->nr_unordered_timestamps++; -static struct trace_sched_handler lat_ops = { - .wakeup_event = latency_wakeup_event, - .switch_event = latency_switch_event, - .runtime_event = latency_runtime_event, - .fork_event = latency_fork_event, - .migrate_task_event = latency_migrate_task_event, -}; + return 0; +} -static void output_lat_thread(struct work_atoms *work_list) +static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list) { int i; int ret; @@ -1214,8 +1113,8 @@ static void output_lat_thread(struct work_atoms *work_list) if (!strcmp(work_list->thread->comm, "swapper")) return; - all_runtime += work_list->total_runtime; - all_count += work_list->nb_atoms; + sched->all_runtime += work_list->total_runtime; + sched->all_count += work_list->nb_atoms; ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->pid); @@ -1241,11 +1140,6 @@ static int pid_cmp(struct work_atoms *l, struct work_atoms *r) return 0; } -static struct sort_dimension pid_sort_dimension = { - .name = "pid", - .cmp = pid_cmp, -}; - static int avg_cmp(struct work_atoms *l, struct work_atoms *r) { u64 avgl, avgr; @@ -1267,11 +1161,6 @@ static int avg_cmp(struct work_atoms *l, struct work_atoms *r) return 0; } -static struct sort_dimension avg_sort_dimension = { - .name = "avg", - .cmp = avg_cmp, -}; - static int max_cmp(struct work_atoms *l, struct work_atoms *r) { if (l->max_lat < r->max_lat) @@ -1282,11 +1171,6 @@ static int max_cmp(struct work_atoms *l, struct work_atoms *r) return 0; } -static struct sort_dimension max_sort_dimension = { - .name = "max", - .cmp = max_cmp, -}; - static int switch_cmp(struct work_atoms *l, struct work_atoms *r) { if (l->nb_atoms < r->nb_atoms) @@ -1297,11 +1181,6 @@ static int switch_cmp(struct work_atoms *l, struct work_atoms *r) return 0; } -static struct sort_dimension switch_sort_dimension = { - .name = "switch", - .cmp = switch_cmp, -}; - static int runtime_cmp(struct work_atoms *l, struct work_atoms *r) { if (l->total_runtime < r->total_runtime) @@ -1312,28 +1191,38 @@ static int runtime_cmp(struct work_atoms *l, struct work_atoms *r) return 0; } -static struct sort_dimension runtime_sort_dimension = { - .name = "runtime", - .cmp = runtime_cmp, -}; - -static struct sort_dimension *available_sorts[] = { - &pid_sort_dimension, - &avg_sort_dimension, - &max_sort_dimension, - &switch_sort_dimension, - &runtime_sort_dimension, -}; - -#define NB_AVAILABLE_SORTS (int)(sizeof(available_sorts) / sizeof(struct sort_dimension *)) - -static LIST_HEAD(sort_list); - static int sort_dimension__add(const char *tok, struct list_head *list) { - int i; + size_t i; + static struct sort_dimension avg_sort_dimension = { + .name = "avg", + .cmp = avg_cmp, + }; + static struct sort_dimension max_sort_dimension = { + .name = "max", + .cmp = max_cmp, + }; + static struct sort_dimension pid_sort_dimension = { + .name = "pid", + .cmp = pid_cmp, + }; + static struct sort_dimension runtime_sort_dimension = { + .name = "runtime", + .cmp = runtime_cmp, + }; + static struct sort_dimension switch_sort_dimension = { + .name = "switch", + .cmp = switch_cmp, + }; + struct sort_dimension *available_sorts[] = { + &pid_sort_dimension, + &avg_sort_dimension, + &max_sort_dimension, + &switch_sort_dimension, + &runtime_sort_dimension, + }; - for (i = 0; i < NB_AVAILABLE_SORTS; i++) { + for (i = 0; i < ARRAY_SIZE(available_sorts); i++) { if (!strcmp(available_sorts[i]->name, tok)) { list_add_tail(&available_sorts[i]->list, list); @@ -1344,126 +1233,97 @@ static int sort_dimension__add(const char *tok, struct list_head *list) return -1; } -static void setup_sorting(void); - -static void sort_lat(void) +static void perf_sched__sort_lat(struct perf_sched *sched) { struct rb_node *node; for (;;) { struct work_atoms *data; - node = rb_first(&atom_root); + node = rb_first(&sched->atom_root); if (!node) break; - rb_erase(node, &atom_root); + rb_erase(node, &sched->atom_root); data = rb_entry(node, struct work_atoms, node); - __thread_latency_insert(&sorted_atom_root, data, &sort_list); + __thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list); } } -static struct trace_sched_handler *trace_handler; - -static void -process_sched_wakeup_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread) +static int process_sched_wakeup_event(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { - void *data = sample->raw_data; - struct trace_wakeup_event wakeup_event; - - FILL_COMMON_FIELDS(wakeup_event, event, data); + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - FILL_ARRAY(wakeup_event, comm, event, data); - FILL_FIELD(wakeup_event, pid, event, data); - FILL_FIELD(wakeup_event, prio, event, data); - FILL_FIELD(wakeup_event, success, event, data); - FILL_FIELD(wakeup_event, cpu, event, data); + if (sched->tp_handler->wakeup_event) + return sched->tp_handler->wakeup_event(sched, evsel, sample, machine); - if (trace_handler->wakeup_event) - trace_handler->wakeup_event(&wakeup_event, machine, event, - sample->cpu, sample->time, thread); + return 0; } -/* - * Track the current task - that way we can know whether there's any - * weird events, such as a task being switched away that is not current. - */ -static int max_cpu; - -static u32 curr_pid[MAX_CPUS] = { [0 ... MAX_CPUS-1] = -1 }; - -static struct thread *curr_thread[MAX_CPUS]; - -static char next_shortname1 = 'A'; -static char next_shortname2 = '0'; - -static void -map_switch_event(struct trace_switch_event *switch_event, - struct machine *machine, - struct event_format *event __used, - int this_cpu, - u64 timestamp, - struct thread *thread __used) +static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, + struct perf_sample *sample, struct machine *machine) { - struct thread *sched_out __used, *sched_in; + const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), + next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + struct thread *sched_out __maybe_unused, *sched_in; int new_shortname; - u64 timestamp0; + u64 timestamp0, timestamp = sample->time; s64 delta; - int cpu; + int cpu, this_cpu = sample->cpu; BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); - if (this_cpu > max_cpu) - max_cpu = this_cpu; + if (this_cpu > sched->max_cpu) + sched->max_cpu = this_cpu; - timestamp0 = cpu_last_switched[this_cpu]; - cpu_last_switched[this_cpu] = timestamp; + timestamp0 = sched->cpu_last_switched[this_cpu]; + sched->cpu_last_switched[this_cpu] = timestamp; if (timestamp0) delta = timestamp - timestamp0; else delta = 0; - if (delta < 0) - die("hm, delta: %" PRIu64 " < 0 ?\n", delta); - + if (delta < 0) { + pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta); + return -1; + } - sched_out = machine__findnew_thread(machine, switch_event->prev_pid); - sched_in = machine__findnew_thread(machine, switch_event->next_pid); + sched_out = machine__findnew_thread(machine, prev_pid); + sched_in = machine__findnew_thread(machine, next_pid); - curr_thread[this_cpu] = sched_in; + sched->curr_thread[this_cpu] = sched_in; printf(" "); new_shortname = 0; if (!sched_in->shortname[0]) { - sched_in->shortname[0] = next_shortname1; - sched_in->shortname[1] = next_shortname2; + sched_in->shortname[0] = sched->next_shortname1; + sched_in->shortname[1] = sched->next_shortname2; - if (next_shortname1 < 'Z') { - next_shortname1++; + if (sched->next_shortname1 < 'Z') { + sched->next_shortname1++; } else { - next_shortname1='A'; - if (next_shortname2 < '9') { - next_shortname2++; + sched->next_shortname1='A'; + if (sched->next_shortname2 < '9') { + sched->next_shortname2++; } else { - next_shortname2='0'; + sched->next_shortname2='0'; } } new_shortname = 1; } - for (cpu = 0; cpu <= max_cpu; cpu++) { + for (cpu = 0; cpu <= sched->max_cpu; cpu++) { if (cpu != this_cpu) printf(" "); else printf("*"); - if (curr_thread[cpu]) { - if (curr_thread[cpu]->pid) - printf("%2s ", curr_thread[cpu]->shortname); + if (sched->curr_thread[cpu]) { + if (sched->curr_thread[cpu]->pid) + printf("%2s ", sched->curr_thread[cpu]->shortname); else printf(". "); } else @@ -1477,134 +1337,97 @@ map_switch_event(struct trace_switch_event *switch_event, } else { printf("\n"); } + + return 0; } -static void -process_sched_switch_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread) +static int process_sched_switch_event(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { - int this_cpu = sample->cpu; - void *data = sample->raw_data; - struct trace_switch_event switch_event; - - FILL_COMMON_FIELDS(switch_event, event, data); - - FILL_ARRAY(switch_event, prev_comm, event, data); - FILL_FIELD(switch_event, prev_pid, event, data); - FILL_FIELD(switch_event, prev_prio, event, data); - FILL_FIELD(switch_event, prev_state, event, data); - FILL_ARRAY(switch_event, next_comm, event, data); - FILL_FIELD(switch_event, next_pid, event, data); - FILL_FIELD(switch_event, next_prio, event, data); + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + int this_cpu = sample->cpu, err = 0; + u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), + next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - if (curr_pid[this_cpu] != (u32)-1) { + if (sched->curr_pid[this_cpu] != (u32)-1) { /* * Are we trying to switch away a PID that is * not current? */ - if (curr_pid[this_cpu] != switch_event.prev_pid) - nr_context_switch_bugs++; + if (sched->curr_pid[this_cpu] != prev_pid) + sched->nr_context_switch_bugs++; } - if (trace_handler->switch_event) - trace_handler->switch_event(&switch_event, machine, event, - this_cpu, sample->time, thread); - curr_pid[this_cpu] = switch_event.next_pid; + if (sched->tp_handler->switch_event) + err = sched->tp_handler->switch_event(sched, evsel, sample, machine); + + sched->curr_pid[this_cpu] = next_pid; + return err; } -static void -process_sched_runtime_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread) +static int process_sched_runtime_event(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { - void *data = sample->raw_data; - struct trace_runtime_event runtime_event; + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - FILL_ARRAY(runtime_event, comm, event, data); - FILL_FIELD(runtime_event, pid, event, data); - FILL_FIELD(runtime_event, runtime, event, data); - FILL_FIELD(runtime_event, vruntime, event, data); + if (sched->tp_handler->runtime_event) + return sched->tp_handler->runtime_event(sched, evsel, sample, machine); - if (trace_handler->runtime_event) - trace_handler->runtime_event(&runtime_event, machine, event, - sample->cpu, sample->time, thread); + return 0; } -static void -process_sched_fork_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample, - struct machine *machine __used, - struct thread *thread) +static int process_sched_fork_event(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine __maybe_unused) { - void *data = sample->raw_data; - struct trace_fork_event fork_event; - - FILL_COMMON_FIELDS(fork_event, event, data); + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - FILL_ARRAY(fork_event, parent_comm, event, data); - FILL_FIELD(fork_event, parent_pid, event, data); - FILL_ARRAY(fork_event, child_comm, event, data); - FILL_FIELD(fork_event, child_pid, event, data); + if (sched->tp_handler->fork_event) + return sched->tp_handler->fork_event(sched, evsel, sample); - if (trace_handler->fork_event) - trace_handler->fork_event(&fork_event, event, - sample->cpu, sample->time, thread); + return 0; } -static void -process_sched_exit_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample __used, - struct machine *machine __used, - struct thread *thread __used) +static int process_sched_exit_event(struct perf_tool *tool __maybe_unused, + struct perf_evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { - if (verbose) - printf("sched_exit event %p\n", event); + pr_debug("sched_exit event %p\n", evsel); + return 0; } -static void -process_sched_migrate_task_event(struct perf_tool *tool __used, - struct event_format *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread) +static int process_sched_migrate_task_event(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine) { - void *data = sample->raw_data; - struct trace_migrate_task_event migrate_task_event; - - FILL_COMMON_FIELDS(migrate_task_event, event, data); + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - FILL_ARRAY(migrate_task_event, comm, event, data); - FILL_FIELD(migrate_task_event, pid, event, data); - FILL_FIELD(migrate_task_event, prio, event, data); - FILL_FIELD(migrate_task_event, cpu, event, data); + if (sched->tp_handler->migrate_task_event) + return sched->tp_handler->migrate_task_event(sched, evsel, sample, machine); - if (trace_handler->migrate_task_event) - trace_handler->migrate_task_event(&migrate_task_event, machine, - event, sample->cpu, - sample->time, thread); + return 0; } -typedef void (*tracepoint_handler)(struct perf_tool *tool, struct event_format *event, - struct perf_sample *sample, - struct machine *machine, - struct thread *thread); +typedef int (*tracepoint_handler)(struct perf_tool *tool, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct machine *machine); -static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, - union perf_event *event __used, +static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine) { - struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - struct pevent *pevent = sched->session->pevent; struct thread *thread = machine__findnew_thread(machine, sample->pid); + int err = 0; if (thread == NULL) { pr_debug("problem processing %s event, skipping it.\n", @@ -1617,30 +1440,15 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, if (evsel->handler.func != NULL) { tracepoint_handler f = evsel->handler.func; - - if (evsel->handler.data == NULL) - evsel->handler.data = pevent_find_event(pevent, - evsel->attr.config); - - f(tool, evsel->handler.data, sample, machine, thread); + err = f(tool, evsel, sample, machine); } - return 0; + return err; } -static struct perf_sched perf_sched = { - .tool = { - .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, - .lost = perf_event__process_lost, - .fork = perf_event__process_task, - .ordered_samples = true, - }, -}; - -static void read_events(bool destroy, struct perf_session **psession) +static int perf_sched__read_events(struct perf_sched *sched, bool destroy, + struct perf_session **psession) { - int err = -EINVAL; const struct perf_evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, { "sched:sched_stat_runtime", process_sched_runtime_event, }, @@ -1652,24 +1460,25 @@ static void read_events(bool destroy, struct perf_session **psession) }; struct perf_session *session; - session = perf_session__new(input_name, O_RDONLY, 0, false, - &perf_sched.tool); - if (session == NULL) - die("No Memory"); - - perf_sched.session = session; + session = perf_session__new(sched->input_name, O_RDONLY, 0, false, &sched->tool); + if (session == NULL) { + pr_debug("No Memory for session\n"); + return -1; + } - err = perf_session__set_tracepoints_handlers(session, handlers); - assert(err == 0); + if (perf_session__set_tracepoints_handlers(session, handlers)) + goto out_delete; if (perf_session__has_traces(session, "record -R")) { - err = perf_session__process_events(session, &perf_sched.tool); - if (err) - die("Failed to process events, error %d", err); + int err = perf_session__process_events(session, &sched->tool); + if (err) { + pr_err("Failed to process events, error %d", err); + goto out_delete; + } - nr_events = session->hists.stats.nr_events[0]; - nr_lost_events = session->hists.stats.total_lost; - nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->hists.stats.nr_events[0]; + sched->nr_lost_events = session->hists.stats.total_lost; + sched->nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST]; } if (destroy) @@ -1677,208 +1486,166 @@ static void read_events(bool destroy, struct perf_session **psession) if (psession) *psession = session; + + return 0; + +out_delete: + perf_session__delete(session); + return -1; } -static void print_bad_events(void) +static void print_bad_events(struct perf_sched *sched) { - if (nr_unordered_timestamps && nr_timestamps) { + if (sched->nr_unordered_timestamps && sched->nr_timestamps) { printf(" INFO: %.3f%% unordered timestamps (%ld out of %ld)\n", - (double)nr_unordered_timestamps/(double)nr_timestamps*100.0, - nr_unordered_timestamps, nr_timestamps); + (double)sched->nr_unordered_timestamps/(double)sched->nr_timestamps*100.0, + sched->nr_unordered_timestamps, sched->nr_timestamps); } - if (nr_lost_events && nr_events) { + if (sched->nr_lost_events && sched->nr_events) { printf(" INFO: %.3f%% lost events (%ld out of %ld, in %ld chunks)\n", - (double)nr_lost_events/(double)nr_events*100.0, - nr_lost_events, nr_events, nr_lost_chunks); + (double)sched->nr_lost_events/(double)sched->nr_events * 100.0, + sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks); } - if (nr_state_machine_bugs && nr_timestamps) { + if (sched->nr_state_machine_bugs && sched->nr_timestamps) { printf(" INFO: %.3f%% state machine bugs (%ld out of %ld)", - (double)nr_state_machine_bugs/(double)nr_timestamps*100.0, - nr_state_machine_bugs, nr_timestamps); - if (nr_lost_events) + (double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0, + sched->nr_state_machine_bugs, sched->nr_timestamps); + if (sched->nr_lost_events) printf(" (due to lost events?)"); printf("\n"); } - if (nr_context_switch_bugs && nr_timestamps) { + if (sched->nr_context_switch_bugs && sched->nr_timestamps) { printf(" INFO: %.3f%% context switch bugs (%ld out of %ld)", - (double)nr_context_switch_bugs/(double)nr_timestamps*100.0, - nr_context_switch_bugs, nr_timestamps); - if (nr_lost_events) + (double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0, + sched->nr_context_switch_bugs, sched->nr_timestamps); + if (sched->nr_lost_events) printf(" (due to lost events?)"); printf("\n"); } } -static void __cmd_lat(void) +static int perf_sched__lat(struct perf_sched *sched) { struct rb_node *next; struct perf_session *session; setup_pager(); - read_events(false, &session); - sort_lat(); + if (perf_sched__read_events(sched, false, &session)) + return -1; + perf_sched__sort_lat(sched); printf("\n ---------------------------------------------------------------------------------------------------------------\n"); printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); printf(" ---------------------------------------------------------------------------------------------------------------\n"); - next = rb_first(&sorted_atom_root); + next = rb_first(&sched->sorted_atom_root); while (next) { struct work_atoms *work_list; work_list = rb_entry(next, struct work_atoms, node); - output_lat_thread(work_list); + output_lat_thread(sched, work_list); next = rb_next(next); } printf(" -----------------------------------------------------------------------------------------\n"); printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", - (double)all_runtime/1e6, all_count); + (double)sched->all_runtime / 1e6, sched->all_count); printf(" ---------------------------------------------------\n"); - print_bad_events(); + print_bad_events(sched); printf("\n"); perf_session__delete(session); + return 0; } -static struct trace_sched_handler map_ops = { - .wakeup_event = NULL, - .switch_event = map_switch_event, - .runtime_event = NULL, - .fork_event = NULL, -}; - -static void __cmd_map(void) +static int perf_sched__map(struct perf_sched *sched) { - max_cpu = sysconf(_SC_NPROCESSORS_CONF); + sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); setup_pager(); - read_events(true, NULL); - print_bad_events(); + if (perf_sched__read_events(sched, true, NULL)) + return -1; + print_bad_events(sched); + return 0; } -static void __cmd_replay(void) +static int perf_sched__replay(struct perf_sched *sched) { unsigned long i; - calibrate_run_measurement_overhead(); - calibrate_sleep_measurement_overhead(); + calibrate_run_measurement_overhead(sched); + calibrate_sleep_measurement_overhead(sched); - test_calibrations(); + test_calibrations(sched); - read_events(true, NULL); + if (perf_sched__read_events(sched, true, NULL)) + return -1; - printf("nr_run_events: %ld\n", nr_run_events); - printf("nr_sleep_events: %ld\n", nr_sleep_events); - printf("nr_wakeup_events: %ld\n", nr_wakeup_events); + printf("nr_run_events: %ld\n", sched->nr_run_events); + printf("nr_sleep_events: %ld\n", sched->nr_sleep_events); + printf("nr_wakeup_events: %ld\n", sched->nr_wakeup_events); - if (targetless_wakeups) - printf("target-less wakeups: %ld\n", targetless_wakeups); - if (multitarget_wakeups) - printf("multi-target wakeups: %ld\n", multitarget_wakeups); - if (nr_run_events_optimized) + if (sched->targetless_wakeups) + printf("target-less wakeups: %ld\n", sched->targetless_wakeups); + if (sched->multitarget_wakeups) + printf("multi-target wakeups: %ld\n", sched->multitarget_wakeups); + if (sched->nr_run_events_optimized) printf("run atoms optimized: %ld\n", - nr_run_events_optimized); + sched->nr_run_events_optimized); - print_task_traces(); - add_cross_task_wakeups(); + print_task_traces(sched); + add_cross_task_wakeups(sched); - create_tasks(); + create_tasks(sched); printf("------------------------------------------------------------\n"); - for (i = 0; i < replay_repeat; i++) - run_one_test(); -} - - -static const char * const sched_usage[] = { - "perf sched [<options>] {record|latency|map|replay|script}", - NULL -}; - -static const struct option sched_options[] = { - OPT_STRING('i', "input", &input_name, "file", - "input file name"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, - "dump raw trace in ASCII"), - OPT_END() -}; - -static const char * const latency_usage[] = { - "perf sched latency [<options>]", - NULL -}; - -static const struct option latency_options[] = { - OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): runtime, switch, avg, max"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_INTEGER('C', "CPU", &profile_cpu, - "CPU to profile on"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, - "dump raw trace in ASCII"), - OPT_END() -}; - -static const char * const replay_usage[] = { - "perf sched replay [<options>]", - NULL -}; + for (i = 0; i < sched->replay_repeat; i++) + run_one_test(sched); -static const struct option replay_options[] = { - OPT_UINTEGER('r', "repeat", &replay_repeat, - "repeat the workload replay N times (-1: infinite)"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, - "dump raw trace in ASCII"), - OPT_END() -}; + return 0; +} -static void setup_sorting(void) +static void setup_sorting(struct perf_sched *sched, const struct option *options, + const char * const usage_msg[]) { - char *tmp, *tok, *str = strdup(sort_order); + char *tmp, *tok, *str = strdup(sched->sort_order); for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - if (sort_dimension__add(tok, &sort_list) < 0) { + if (sort_dimension__add(tok, &sched->sort_list) < 0) { error("Unknown --sort key: `%s'", tok); - usage_with_options(latency_usage, latency_options); + usage_with_options(usage_msg, options); } } free(str); - sort_dimension__add("pid", &cmp_pid); + sort_dimension__add("pid", &sched->cmp_pid); } -static const char *record_args[] = { - "record", - "-a", - "-R", - "-f", - "-m", "1024", - "-c", "1", - "-e", "sched:sched_switch", - "-e", "sched:sched_stat_wait", - "-e", "sched:sched_stat_sleep", - "-e", "sched:sched_stat_iowait", - "-e", "sched:sched_stat_runtime", - "-e", "sched:sched_process_exit", - "-e", "sched:sched_process_fork", - "-e", "sched:sched_wakeup", - "-e", "sched:sched_migrate_task", -}; - static int __cmd_record(int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; + const char * const record_args[] = { + "record", + "-a", + "-R", + "-f", + "-m", "1024", + "-c", "1", + "-e", "sched:sched_switch", + "-e", "sched:sched_stat_wait", + "-e", "sched:sched_stat_sleep", + "-e", "sched:sched_stat_iowait", + "-e", "sched:sched_stat_runtime", + "-e", "sched:sched_process_exit", + "-e", "sched:sched_process_fork", + "-e", "sched:sched_wakeup", + "-e", "sched:sched_migrate_task", + }; rec_argc = ARRAY_SIZE(record_args) + argc - 1; rec_argv = calloc(rec_argc + 1, sizeof(char *)); @@ -1897,8 +1664,85 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -int cmd_sched(int argc, const char **argv, const char *prefix __used) +int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) { + const char default_sort_order[] = "avg, max, switch, runtime"; + struct perf_sched sched = { + .tool = { + .sample = perf_sched__process_tracepoint_sample, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_task, + .ordered_samples = true, + }, + .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), + .sort_list = LIST_HEAD_INIT(sched.sort_list), + .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, + .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, + .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, + .sort_order = default_sort_order, + .replay_repeat = 10, + .profile_cpu = -1, + .next_shortname1 = 'A', + .next_shortname2 = '0', + }; + const struct option latency_options[] = { + OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]", + "sort by key(s): runtime, switch, avg, max"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_INTEGER('C', "CPU", &sched.profile_cpu, + "CPU to profile on"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_END() + }; + const struct option replay_options[] = { + OPT_UINTEGER('r', "repeat", &sched.replay_repeat, + "repeat the workload replay N times (-1: infinite)"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_END() + }; + const struct option sched_options[] = { + OPT_STRING('i', "input", &sched.input_name, "file", + "input file name"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_END() + }; + const char * const latency_usage[] = { + "perf sched latency [<options>]", + NULL + }; + const char * const replay_usage[] = { + "perf sched replay [<options>]", + NULL + }; + const char * const sched_usage[] = { + "perf sched [<options>] {record|latency|map|replay|script}", + NULL + }; + struct trace_sched_handler lat_ops = { + .wakeup_event = latency_wakeup_event, + .switch_event = latency_switch_event, + .runtime_event = latency_runtime_event, + .fork_event = latency_fork_event, + .migrate_task_event = latency_migrate_task_event, + }; + struct trace_sched_handler map_ops = { + .switch_event = map_switch_event, + }; + struct trace_sched_handler replay_ops = { + .wakeup_event = replay_wakeup_event, + .switch_event = replay_switch_event, + .fork_event = replay_fork_event, + }; + argc = parse_options(argc, argv, sched_options, sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) @@ -1914,26 +1758,26 @@ int cmd_sched(int argc, const char **argv, const char *prefix __used) if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strncmp(argv[0], "lat", 3)) { - trace_handler = &lat_ops; + sched.tp_handler = &lat_ops; if (argc > 1) { argc = parse_options(argc, argv, latency_options, latency_usage, 0); if (argc) usage_with_options(latency_usage, latency_options); } - setup_sorting(); - __cmd_lat(); + setup_sorting(&sched, latency_options, latency_usage); + return perf_sched__lat(&sched); } else if (!strcmp(argv[0], "map")) { - trace_handler = &map_ops; - setup_sorting(); - __cmd_map(); + sched.tp_handler = &map_ops; + setup_sorting(&sched, latency_options, latency_usage); + return perf_sched__map(&sched); } else if (!strncmp(argv[0], "rep", 3)) { - trace_handler = &replay_ops; + sched.tp_handler = &replay_ops; if (argc) { argc = parse_options(argc, argv, replay_options, replay_usage, 0); if (argc) usage_with_options(replay_usage, replay_options); } - __cmd_replay(); + return perf_sched__replay(&sched); } else { usage_with_options(sched_usage, sched_options); } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 1e60ab70b2b1..1be843aa1546 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -14,6 +14,7 @@ #include "util/util.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/sort.h" #include <linux/bitmap.h> static char const *script_name; @@ -28,11 +29,6 @@ static bool system_wide; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); -struct perf_script { - struct perf_tool tool; - struct perf_session *session; -}; - enum perf_output_field { PERF_OUTPUT_COMM = 1U << 0, PERF_OUTPUT_TID = 1U << 1, @@ -262,14 +258,11 @@ static int perf_session__check_output_opt(struct perf_session *session) return 0; } -static void print_sample_start(struct pevent *pevent, - struct perf_sample *sample, +static void print_sample_start(struct perf_sample *sample, struct thread *thread, struct perf_evsel *evsel) { - int type; struct perf_event_attr *attr = &evsel->attr; - struct event_format *event; const char *evname = NULL; unsigned long secs; unsigned long usecs; @@ -307,20 +300,7 @@ static void print_sample_start(struct pevent *pevent, } if (PRINT_FIELD(EVNAME)) { - if (attr->type == PERF_TYPE_TRACEPOINT) { - /* - * XXX Do we really need this here? - * perf_evlist__set_tracepoint_names should have done - * this already - */ - type = trace_parse_common_type(pevent, - sample->raw_data); - event = pevent_find_event(pevent, type); - if (event) - evname = event->name; - } else - evname = perf_evsel__name(evsel); - + evname = perf_evsel__name(evsel); printf("%s: ", evname ? evname : "[unknown]"); } } @@ -401,7 +381,7 @@ static void print_sample_bts(union perf_event *event, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, + perf_evsel__print_ip(evsel, event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -415,19 +395,17 @@ static void print_sample_bts(union perf_event *event, printf("\n"); } -static void process_event(union perf_event *event __unused, - struct pevent *pevent, - struct perf_sample *sample, - struct perf_evsel *evsel, - struct machine *machine, - struct thread *thread) +static void process_event(union perf_event *event, struct perf_sample *sample, + struct perf_evsel *evsel, struct machine *machine, + struct addr_location *al) { struct perf_event_attr *attr = &evsel->attr; + struct thread *thread = al->thread; if (output[attr->type].fields == 0) return; - print_sample_start(pevent, sample, thread, evsel); + print_sample_start(sample, thread, evsel); if (is_bts_event(attr)) { print_sample_bts(event, sample, evsel, machine, thread); @@ -435,9 +413,8 @@ static void process_event(union perf_event *event __unused, } if (PRINT_FIELD(TRACE)) - print_trace_event(pevent, sample->cpu, sample->raw_data, - sample->raw_size); - + event_format__print(evsel->tp_format, sample->cpu, + sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) print_sample_addr(event, sample, machine, thread, attr); @@ -446,7 +423,7 @@ static void process_event(union perf_event *event __unused, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, + perf_evsel__print_ip(evsel, event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -454,9 +431,9 @@ static void process_event(union perf_event *event __unused, printf("\n"); } -static int default_start_script(const char *script __unused, - int argc __unused, - const char **argv __unused) +static int default_start_script(const char *script __maybe_unused, + int argc __maybe_unused, + const char **argv __maybe_unused) { return 0; } @@ -466,8 +443,8 @@ static int default_stop_script(void) return 0; } -static int default_generate_script(struct pevent *pevent __unused, - const char *outfile __unused) +static int default_generate_script(struct pevent *pevent __maybe_unused, + const char *outfile __maybe_unused) { return 0; } @@ -498,14 +475,13 @@ static int cleanup_scripting(void) static const char *input_name; -static int process_sample_event(struct perf_tool *tool __used, +static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine) { struct addr_location al; - struct perf_script *scr = container_of(tool, struct perf_script, tool); struct thread *thread = machine__findnew_thread(machine, event->ip.tid); if (thread == NULL) { @@ -537,32 +513,29 @@ static int process_sample_event(struct perf_tool *tool __used, if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) return 0; - scripting_ops->process_event(event, scr->session->pevent, - sample, evsel, machine, thread); + scripting_ops->process_event(event, sample, evsel, machine, &al); evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_script perf_script = { - .tool = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, - .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, - .tracing_data = perf_event__process_tracing_data, - .build_id = perf_event__process_build_id, - .ordered_samples = true, - .ordering_requires_timestamps = true, - }, +static struct perf_tool perf_script = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .attr = perf_event__process_attr, + .event_type = perf_event__process_event_type, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + .ordering_requires_timestamps = true, }; extern volatile int session_done; -static void sig_handler(int sig __unused) +static void sig_handler(int sig __maybe_unused) { session_done = 1; } @@ -573,7 +546,7 @@ static int __cmd_script(struct perf_session *session) signal(SIGINT, sig_handler); - ret = perf_session__process_events(session, &perf_script.tool); + ret = perf_session__process_events(session, &perf_script); if (debug_mode) pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); @@ -672,8 +645,8 @@ static void list_available_languages(void) fprintf(stderr, "\n"); } -static int parse_scriptname(const struct option *opt __used, - const char *str, int unset __used) +static int parse_scriptname(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) { char spec[PATH_MAX]; const char *script, *ext; @@ -718,8 +691,8 @@ static int parse_scriptname(const struct option *opt __used, return 0; } -static int parse_output_fields(const struct option *opt __used, - const char *arg, int unset __used) +static int parse_output_fields(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) { char *tok; int i, imax = sizeof(all_output_options) / sizeof(struct output_option); @@ -1010,8 +983,9 @@ static char *get_script_root(struct dirent *script_dirent, const char *suffix) return script_root; } -static int list_available_scripts(const struct option *opt __used, - const char *s __used, int unset __used) +static int list_available_scripts(const struct option *opt __maybe_unused, + const char *s __maybe_unused, + int unset __maybe_unused) { struct dirent *script_next, *lang_next, script_dirent, lang_dirent; char scripts_path[MAXPATHLEN]; @@ -1058,6 +1032,61 @@ static int list_available_scripts(const struct option *opt __used, exit(0); } +/* + * Return -1 if none is found, otherwise the actual scripts number. + * + * Currently the only user of this function is the script browser, which + * will list all statically runnable scripts, select one, execute it and + * show the output in a perf browser. + */ +int find_scripts(char **scripts_array, char **scripts_path_array) +{ + struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + char scripts_path[MAXPATHLEN]; + DIR *scripts_dir, *lang_dir; + char lang_path[MAXPATHLEN]; + char *temp; + int i = 0; + + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + + scripts_dir = opendir(scripts_path); + if (!scripts_dir) + return -1; + + for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, + lang_dirent.d_name); +#ifdef NO_LIBPERL + if (strstr(lang_path, "perl")) + continue; +#endif +#ifdef NO_LIBPYTHON + if (strstr(lang_path, "python")) + continue; +#endif + + lang_dir = opendir(lang_path); + if (!lang_dir) + continue; + + for_each_script(lang_path, lang_dir, script_dirent, script_next) { + /* Skip those real time scripts: xxxtop.p[yl] */ + if (strstr(script_dirent.d_name, "top.")) + continue; + sprintf(scripts_path_array[i], "%s/%s", lang_path, + script_dirent.d_name); + temp = strchr(script_dirent.d_name, '.'); + snprintf(scripts_array[i], + (temp - script_dirent.d_name) + 1, + "%s", script_dirent.d_name); + i++; + } + } + + return i; +} + static char *get_script_path(const char *script_root, const char *suffix) { struct dirent *script_next, *lang_next, script_dirent, lang_dirent; @@ -1170,6 +1199,8 @@ static const struct option options[] = { parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), + OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", + "only consider these symbols"), OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", "only display events for these comms"), @@ -1181,21 +1212,26 @@ static const struct option options[] = { OPT_END() }; -static bool have_cmd(int argc, const char **argv) +static int have_cmd(int argc, const char **argv) { char **__argv = malloc(sizeof(const char *) * argc); - if (!__argv) - die("malloc"); + if (!__argv) { + pr_err("malloc failed\n"); + return -1; + } + memcpy(__argv, argv, sizeof(const char *) * argc); argc = parse_options(argc, (const char **)__argv, record_options, NULL, PARSE_OPT_STOP_AT_NON_OPTION); free(__argv); - return argc != 0; + system_wide = (argc == 0); + + return 0; } -int cmd_script(int argc, const char **argv, const char *prefix __used) +int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) { char *rec_script_path = NULL; char *rep_script_path = NULL; @@ -1259,13 +1295,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) if (pipe(live_pipe) < 0) { perror("failed to create pipe"); - exit(-1); + return -1; } pid = fork(); if (pid < 0) { perror("failed to fork"); - exit(-1); + return -1; } if (!pid) { @@ -1277,13 +1313,18 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) if (is_top_script(argv[0])) { system_wide = true; } else if (!system_wide) { - system_wide = !have_cmd(argc - rep_args, - &argv[rep_args]); + if (have_cmd(argc - rep_args, &argv[rep_args]) != 0) { + err = -1; + goto out; + } } __argv = malloc((argc + 6) * sizeof(const char *)); - if (!__argv) - die("malloc"); + if (!__argv) { + pr_err("malloc failed\n"); + err = -ENOMEM; + goto out; + } __argv[j++] = "/bin/sh"; __argv[j++] = rec_script_path; @@ -1305,8 +1346,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) close(live_pipe[1]); __argv = malloc((argc + 4) * sizeof(const char *)); - if (!__argv) - die("malloc"); + if (!__argv) { + pr_err("malloc failed\n"); + err = -ENOMEM; + goto out; + } + j = 0; __argv[j++] = "/bin/sh"; __argv[j++] = rep_script_path; @@ -1331,12 +1376,20 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) if (!rec_script_path) system_wide = false; - else if (!system_wide) - system_wide = !have_cmd(argc - 1, &argv[1]); + else if (!system_wide) { + if (have_cmd(argc - 1, &argv[1]) != 0) { + err = -1; + goto out; + } + } __argv = malloc((argc + 2) * sizeof(const char *)); - if (!__argv) - die("malloc"); + if (!__argv) { + pr_err("malloc failed\n"); + err = -ENOMEM; + goto out; + } + __argv[j++] = "/bin/sh"; __argv[j++] = script_path; if (system_wide) @@ -1356,12 +1409,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) setup_pager(); session = perf_session__new(input_name, O_RDONLY, 0, false, - &perf_script.tool); + &perf_script); if (session == NULL) return -ENOMEM; - perf_script.session = session; - if (cpu_list) { if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) return -1; @@ -1387,18 +1438,18 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) input = open(session->filename, O_RDONLY); /* input_name */ if (input < 0) { perror("failed to open file"); - exit(-1); + return -1; } err = fstat(input, &perf_stat); if (err < 0) { perror("failed to stat file"); - exit(-1); + return -1; } if (!perf_stat.st_size) { fprintf(stderr, "zero-sized file, nothing to do!\n"); - exit(0); + return 0; } scripting_ops = script_spec__lookup(generate_script_lang); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 861f0aec77ae..e8cd4d81b06e 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -51,13 +51,13 @@ #include "util/evsel.h" #include "util/debug.h" #include "util/color.h" +#include "util/stat.h" #include "util/header.h" #include "util/cpumap.h" #include "util/thread.h" #include "util/thread_map.h" #include <sys/prctl.h> -#include <math.h> #include <locale.h> #define DEFAULT_SEPARATOR " " @@ -199,11 +199,6 @@ static int output_fd; static volatile int done = 0; -struct stats -{ - double n, mean, M2; -}; - struct perf_stat { struct stats res_stats[3]; }; @@ -220,48 +215,14 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) evsel->priv = NULL; } -static void update_stats(struct stats *stats, u64 val) -{ - double delta; - - stats->n++; - delta = val - stats->mean; - stats->mean += delta / stats->n; - stats->M2 += delta*(val - stats->mean); -} - -static double avg_stats(struct stats *stats) +static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) { - return stats->mean; + return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; } -/* - * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance - * - * (\Sum n_i^2) - ((\Sum n_i)^2)/n - * s^2 = ------------------------------- - * n - 1 - * - * http://en.wikipedia.org/wiki/Stddev - * - * The std dev of the mean is related to the std dev by: - * - * s - * s_mean = ------- - * sqrt(n) - * - */ -static double stddev_stats(struct stats *stats) +static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) { - double variance, variance_mean; - - if (!stats->n) - return 0.0; - - variance = stats->M2 / (stats->n - 1); - variance_mean = variance / stats->n; - - return sqrt(variance_mean); + return perf_evsel__cpus(evsel)->nr; } static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; @@ -281,13 +242,9 @@ static int create_perf_stat_counter(struct perf_evsel *evsel, struct perf_evsel *first) { struct perf_event_attr *attr = &evsel->attr; - struct xyarray *group_fd = NULL; bool exclude_guest_missing = false; int ret; - if (group && evsel != first) - group_fd = first->fd; - if (scale) attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; @@ -299,8 +256,7 @@ retry: evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; if (perf_target__has_cpu(&target)) { - ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus, - group, group_fd); + ret = perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); if (ret) goto check_ret; return 0; @@ -311,8 +267,7 @@ retry: attr->enable_on_exec = 1; } - ret = perf_evsel__open_per_thread(evsel, evsel_list->threads, - group, group_fd); + ret = perf_evsel__open_per_thread(evsel, evsel_list->threads); if (!ret) return 0; /* fall through */ @@ -382,7 +337,7 @@ static int read_counter_aggr(struct perf_evsel *counter) u64 *count = counter->counts->aggr.values; int i; - if (__perf_evsel__read(counter, evsel_list->cpus->nr, + if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter), evsel_list->threads->nr, scale) < 0) return -1; @@ -411,7 +366,7 @@ static int read_counter(struct perf_evsel *counter) u64 *count; int cpu; - for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) { + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0) return -1; @@ -423,7 +378,7 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static int run_perf_stat(int argc __used, const char **argv) +static int run_perf_stat(int argc __maybe_unused, const char **argv) { unsigned long long t0, t1; struct perf_evsel *counter, *first; @@ -434,7 +389,7 @@ static int run_perf_stat(int argc __used, const char **argv) if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) { perror("failed to create pipes"); - exit(1); + return -1; } if (forks) { @@ -483,7 +438,10 @@ static int run_perf_stat(int argc __used, const char **argv) close(child_ready_pipe[0]); } - first = list_entry(evsel_list->entries.next, struct perf_evsel, node); + if (group) + perf_evlist__set_leader(evsel_list); + + first = perf_evlist__first(evsel_list); list_for_each_entry(counter, &evsel_list->entries, node) { if (create_perf_stat_counter(counter, first) < 0) { @@ -513,13 +471,14 @@ static int run_perf_stat(int argc __used, const char **argv) } if (child_pid != -1) kill(child_pid, SIGTERM); - die("Not all events could be opened.\n"); + + pr_err("Not all events could be opened.\n"); return -1; } counter->supported = true; } - if (perf_evlist__set_filters(evsel_list)) { + if (perf_evlist__apply_filters(evsel_list)) { error("failed to set filter with %d (%s)\n", errno, strerror(errno)); return -1; @@ -546,12 +505,12 @@ static int run_perf_stat(int argc __used, const char **argv) if (no_aggr) { list_for_each_entry(counter, &evsel_list->entries, node) { read_counter(counter); - perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1); + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1); } } else { list_for_each_entry(counter, &evsel_list->entries, node) { read_counter_aggr(counter); - perf_evsel__close_fd(counter, evsel_list->cpus->nr, + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), evsel_list->threads->nr); } } @@ -561,10 +520,7 @@ static int run_perf_stat(int argc __used, const char **argv) static void print_noise_pct(double total, double avg) { - double pct = 0.0; - - if (avg) - pct = 100.0*total/avg; + double pct = rel_stddev_stats(total, avg); if (csv_output) fprintf(output, "%s%.2f%%", csv_sep, pct); @@ -592,7 +548,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, - evsel_list->cpus->map[cpu], csv_sep); + perf_evsel__cpus(evsel)->map[cpu], csv_sep); fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel)); @@ -636,7 +592,9 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_stalled_cycles_frontend(int cpu, + struct perf_evsel *evsel + __maybe_unused, double avg) { double total, ratio = 0.0; const char *color; @@ -653,7 +611,9 @@ static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __us fprintf(output, " frontend cycles idle "); } -static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_stalled_cycles_backend(int cpu, + struct perf_evsel *evsel + __maybe_unused, double avg) { double total, ratio = 0.0; const char *color; @@ -670,7 +630,9 @@ static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __use fprintf(output, " backend cycles idle "); } -static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_branch_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -687,7 +649,9 @@ static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double fprintf(output, " of all branches "); } -static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_l1_dcache_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -704,7 +668,9 @@ static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, dou fprintf(output, " of all L1-dcache hits "); } -static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_l1_icache_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -721,7 +687,9 @@ static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, dou fprintf(output, " of all L1-icache hits "); } -static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_dtlb_cache_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -738,7 +706,9 @@ static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do fprintf(output, " of all dTLB cache hits "); } -static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_itlb_cache_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -755,7 +725,9 @@ static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do fprintf(output, " of all iTLB cache hits "); } -static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) +static void print_ll_cache_misses(int cpu, + struct perf_evsel *evsel __maybe_unused, + double avg) { double total, ratio = 0.0; const char *color; @@ -788,7 +760,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, - evsel_list->cpus->map[cpu], csv_sep); + perf_evsel__cpus(evsel)->map[cpu], csv_sep); else cpu = 0; @@ -949,14 +921,14 @@ static void print_counter(struct perf_evsel *counter) u64 ena, run, val; int cpu; - for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) { + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { val = counter->counts->cpu[cpu].val; ena = counter->counts->cpu[cpu].ena; run = counter->counts->cpu[cpu].run; if (run == 0 || ena == 0) { fprintf(output, "CPU%*d%s%*s%s%*s", csv_output ? 0 : -4, - evsel_list->cpus->map[cpu], csv_sep, + perf_evsel__cpus(counter)->map[cpu], csv_sep, csv_output ? 0 : 18, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, @@ -1061,8 +1033,8 @@ static const char * const stat_usage[] = { NULL }; -static int stat__set_big_num(const struct option *opt __used, - const char *s __used, int unset) +static int stat__set_big_num(const struct option *opt __maybe_unused, + const char *s __maybe_unused, int unset) { big_num_opt = unset ? 0 : 1; return 0; @@ -1156,7 +1128,7 @@ static int add_default_attributes(void) return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs); } -int cmd_stat(int argc, const char **argv, const char *prefix __used) +int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_evsel *pos; int status = -ENOMEM; @@ -1192,7 +1164,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) output = fopen(output_name, mode); if (!output) { perror("failed to create output file"); - exit(-1); + return -1; } clock_gettime(CLOCK_REALTIME, &tm); fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); @@ -1255,7 +1227,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) list_for_each_entry(pos, &evsel_list->entries, node) { if (perf_evsel__alloc_stat_priv(pos) < 0 || - perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0) + perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0) goto out_free_fd; } diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 1d592f5cbea9..484f26cc0c00 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -14,11 +14,13 @@ #include "util/symbol.h" #include "util/thread_map.h" #include "util/pmu.h" +#include "event-parse.h" #include "../../include/linux/hw_breakpoint.h" #include <sys/mman.h> -static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym) +static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused, + struct symbol *sym) { bool *visited = symbol__priv(sym); *visited = true; @@ -294,7 +296,7 @@ static int test__open_syscall_event(void) goto out_thread_map_delete; } - if (perf_evsel__open_per_thread(evsel, threads, false, NULL) < 0) { + if (perf_evsel__open_per_thread(evsel, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", strerror(errno)); @@ -369,7 +371,7 @@ static int test__open_syscall_event_on_all_cpus(void) goto out_thread_map_delete; } - if (perf_evsel__open(evsel, cpus, threads, false, NULL) < 0) { + if (perf_evsel__open(evsel, cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", strerror(errno)); @@ -533,7 +535,7 @@ static int test__basic_mmap(void) perf_evlist__add(evlist, evsels[i]); - if (perf_evsel__open(evsels[i], cpus, threads, false, NULL) < 0) { + if (perf_evsel__open(evsels[i], cpus, threads) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", strerror(errno)); @@ -562,7 +564,7 @@ static int test__basic_mmap(void) goto out_munmap; } - err = perf_evlist__parse_sample(evlist, event, &sample, false); + err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { pr_err("Can't parse sample, err = %d\n", err); goto out_munmap; @@ -710,7 +712,7 @@ static int test__PERF_RECORD(void) /* * Config the evsels, setting attr->comm on the first one, etc. */ - evsel = list_entry(evlist->entries.next, struct perf_evsel, node); + evsel = perf_evlist__first(evlist); evsel->attr.sample_type |= PERF_SAMPLE_CPU; evsel->attr.sample_type |= PERF_SAMPLE_TID; evsel->attr.sample_type |= PERF_SAMPLE_TIME; @@ -737,7 +739,7 @@ static int test__PERF_RECORD(void) * Call sys_perf_event_open on all the fds on all the evsels, * grouping them if asked to. */ - err = perf_evlist__open(evlist, opts.group); + err = perf_evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", strerror(errno)); goto out_delete_evlist; @@ -779,7 +781,7 @@ static int test__PERF_RECORD(void) if (type < PERF_RECORD_MAX) nr_events[type]++; - err = perf_evlist__parse_sample(evlist, event, &sample, false); + err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { if (verbose) perf_event__fprintf(event, stderr); @@ -996,7 +998,9 @@ static u64 mmap_read_self(void *addr) /* * If the RDPMC instruction faults then signal this back to the test parent task: */ -static void segfault_handler(int sig __used, siginfo_t *info __used, void *uc __used) +static void segfault_handler(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) { exit(-1); } @@ -1023,14 +1027,16 @@ static int __test__rdpmc(void) fd = sys_perf_event_open(&attr, 0, -1, -1, 0); if (fd < 0) { - die("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); + pr_err("Error: sys_perf_event_open() syscall returned " + "with %d (%s)\n", fd, strerror(errno)); + return -1; } addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); if (addr == (void *)(-1)) { - die("Error: mmap() syscall returned " - "with (%s)\n", strerror(errno)); + pr_err("Error: mmap() syscall returned with (%s)\n", + strerror(errno)); + goto out_close; } for (n = 0; n < 6; n++) { @@ -1051,9 +1057,9 @@ static int __test__rdpmc(void) } munmap(addr, page_size); - close(fd); - pr_debug(" "); +out_close: + close(fd); if (!delta_sum) return -1; @@ -1092,6 +1098,309 @@ static int test__perf_pmu(void) return perf_pmu__test(); } +static int perf_evsel__roundtrip_cache_name_test(void) +{ + char name[128]; + int type, op, err = 0, ret = 0, i, idx; + struct perf_evsel *evsel; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + + if (evlist == NULL) + return -ENOMEM; + + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!perf_evsel__is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); + err = parse_events(evlist, name, 0); + if (err) + ret = err; + } + } + } + + idx = 0; + evsel = perf_evlist__first(evlist); + + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!perf_evsel__is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); + if (evsel->idx != idx) + continue; + + ++idx; + + if (strcmp(perf_evsel__name(evsel), name)) { + pr_debug("%s != %s\n", perf_evsel__name(evsel), name); + ret = -1; + } + + evsel = perf_evsel__next(evsel); + } + } + } + + perf_evlist__delete(evlist); + return ret; +} + +static int __perf_evsel__name_array_test(const char *names[], int nr_names) +{ + int i, err; + struct perf_evsel *evsel; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + + if (evlist == NULL) + return -ENOMEM; + + for (i = 0; i < nr_names; ++i) { + err = parse_events(evlist, names[i], 0); + if (err) { + pr_debug("failed to parse event '%s', err %d\n", + names[i], err); + goto out_delete_evlist; + } + } + + err = 0; + list_for_each_entry(evsel, &evlist->entries, node) { + if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) { + --err; + pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]); + } + } + +out_delete_evlist: + perf_evlist__delete(evlist); + return err; +} + +#define perf_evsel__name_array_test(names) \ + __perf_evsel__name_array_test(names, ARRAY_SIZE(names)) + +static int perf_evsel__roundtrip_name_test(void) +{ + int err = 0, ret = 0; + + err = perf_evsel__name_array_test(perf_evsel__hw_names); + if (err) + ret = err; + + err = perf_evsel__name_array_test(perf_evsel__sw_names); + if (err) + ret = err; + + err = perf_evsel__roundtrip_cache_name_test(); + if (err) + ret = err; + + return ret; +} + +static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, + int size, bool should_be_signed) +{ + struct format_field *field = perf_evsel__field(evsel, name); + int is_signed; + int ret = 0; + + if (field == NULL) { + pr_debug("%s: \"%s\" field not found!\n", evsel->name, name); + return -1; + } + + is_signed = !!(field->flags | FIELD_IS_SIGNED); + if (should_be_signed && !is_signed) { + pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", + evsel->name, name, is_signed, should_be_signed); + ret = -1; + } + + if (field->size != size) { + pr_debug("%s: \"%s\" size (%d) should be %d!\n", + evsel->name, name, field->size, size); + ret = -1; + } + + return ret; +} + +static int perf_evsel__tp_sched_test(void) +{ + struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0); + int ret = 0; + + if (evsel == NULL) { + pr_debug("perf_evsel__new\n"); + return -1; + } + + if (perf_evsel__test_field(evsel, "prev_comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_state", 8, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_prio", 4, true)) + ret = -1; + + perf_evsel__delete(evsel); + + evsel = perf_evsel__newtp("sched", "sched_wakeup", 0); + + if (perf_evsel__test_field(evsel, "comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prio", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "success", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) + ret = -1; + + return ret; +} + +static int test__syscall_open_tp_fields(void) +{ + struct perf_record_opts opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, + .no_delay = true, + .freq = 1, + .mmap_pages = 256, + .raw_samples = true, + }; + const char *filename = "/etc/passwd"; + int flags = O_RDONLY | O_DIRECTORY; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evsel *evsel; + int err = -1, i, nr_events = 0, nr_polls = 0; + + if (evlist == NULL) { + pr_debug("%s: perf_evlist__new\n", __func__); + goto out; + } + + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); + if (evsel == NULL) { + pr_debug("%s: perf_evsel__newtp\n", __func__); + goto out_delete_evlist; + } + + perf_evlist__add(evlist, evsel); + + err = perf_evlist__create_maps(evlist, &opts.target); + if (err < 0) { + pr_debug("%s: perf_evlist__create_maps\n", __func__); + goto out_delete_evlist; + } + + perf_evsel__config(evsel, &opts, evsel); + + evlist->threads->map[0] = getpid(); + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + err = perf_evlist__mmap(evlist, UINT_MAX, false); + if (err < 0) { + pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + perf_evlist__enable(evlist); + + /* + * Generate the event: + */ + open(filename, flags); + + while (1) { + int before = nr_events; + + for (i = 0; i < evlist->nr_mmaps; i++) { + union perf_event *event; + + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + const u32 type = event->header.type; + int tp_flags; + struct perf_sample sample; + + ++nr_events; + + if (type != PERF_RECORD_SAMPLE) + continue; + + err = perf_evsel__parse_sample(evsel, event, &sample); + if (err) { + pr_err("Can't parse sample, err = %d\n", err); + goto out_munmap; + } + + tp_flags = perf_evsel__intval(evsel, &sample, "flags"); + + if (flags != tp_flags) { + pr_debug("%s: Expected flags=%#x, got %#x\n", + __func__, flags, tp_flags); + goto out_munmap; + } + + goto out_ok; + } + } + + if (nr_events == before) + poll(evlist->pollfd, evlist->nr_fds, 10); + + if (++nr_polls > 5) { + pr_debug("%s: no events!\n", __func__); + goto out_munmap; + } + } +out_ok: + err = 0; +out_munmap: + perf_evlist__munmap(evlist); +out_delete_evlist: + perf_evlist__delete(evlist); +out: + return err; +} + static struct test { const char *desc; int (*func)(void); @@ -1135,6 +1444,18 @@ static struct test { .func = dso__test_data, }, { + .desc = "roundtrip evsel->name check", + .func = perf_evsel__roundtrip_name_test, + }, + { + .desc = "Check parsing of sched tracepoints fields", + .func = perf_evsel__tp_sched_test, + }, + { + .desc = "Generate and check syscalls:sys_enter_open event fields", + .func = test__syscall_open_tp_fields, + }, + { .func = NULL, }, }; @@ -1199,7 +1520,7 @@ static int perf_test__list(int argc, const char **argv) return 0; } -int cmd_test(int argc, const char **argv, const char *prefix __used) +int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const test_usage[] = { "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 3b75b2e21ea5..b1a8a3b841cc 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -168,9 +168,8 @@ static struct per_pid *find_create_pid(int pid) return cursor; cursor = cursor->next; } - cursor = malloc(sizeof(struct per_pid)); + cursor = zalloc(sizeof(*cursor)); assert(cursor != NULL); - memset(cursor, 0, sizeof(struct per_pid)); cursor->pid = pid; cursor->next = all_data; all_data = cursor; @@ -195,9 +194,8 @@ static void pid_set_comm(int pid, char *comm) } c = c->next; } - c = malloc(sizeof(struct per_pidcomm)); + c = zalloc(sizeof(*c)); assert(c != NULL); - memset(c, 0, sizeof(struct per_pidcomm)); c->comm = strdup(comm); p->current = c; c->next = p->all; @@ -239,17 +237,15 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end) p = find_create_pid(pid); c = p->current; if (!c) { - c = malloc(sizeof(struct per_pidcomm)); + c = zalloc(sizeof(*c)); assert(c != NULL); - memset(c, 0, sizeof(struct per_pidcomm)); p->current = c; c->next = p->all; p->all = c; } - sample = malloc(sizeof(struct cpu_sample)); + sample = zalloc(sizeof(*sample)); assert(sample != NULL); - memset(sample, 0, sizeof(struct cpu_sample)); sample->start_time = start; sample->end_time = end; sample->type = type; @@ -275,28 +271,28 @@ static int cpus_cstate_state[MAX_CPUS]; static u64 cpus_pstate_start_times[MAX_CPUS]; static u64 cpus_pstate_state[MAX_CPUS]; -static int process_comm_event(struct perf_tool *tool __used, +static int process_comm_event(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, - struct machine *machine __used) + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { pid_set_comm(event->comm.tid, event->comm.comm); return 0; } -static int process_fork_event(struct perf_tool *tool __used, +static int process_fork_event(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, - struct machine *machine __used) + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { pid_fork(event->fork.pid, event->fork.ppid, event->fork.time); return 0; } -static int process_exit_event(struct perf_tool *tool __used, +static int process_exit_event(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, - struct machine *machine __used) + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { pid_exit(event->fork.pid, event->fork.time); return 0; @@ -373,11 +369,10 @@ static void c_state_start(int cpu, u64 timestamp, int state) static void c_state_end(int cpu, u64 timestamp) { - struct power_event *pwr; - pwr = malloc(sizeof(struct power_event)); + struct power_event *pwr = zalloc(sizeof(*pwr)); + if (!pwr) return; - memset(pwr, 0, sizeof(struct power_event)); pwr->state = cpus_cstate_state[cpu]; pwr->start_time = cpus_cstate_start_times[cpu]; @@ -392,14 +387,13 @@ static void c_state_end(int cpu, u64 timestamp) static void p_state_change(int cpu, u64 timestamp, u64 new_freq) { struct power_event *pwr; - pwr = malloc(sizeof(struct power_event)); if (new_freq > 8000000) /* detect invalid data */ return; + pwr = zalloc(sizeof(*pwr)); if (!pwr) return; - memset(pwr, 0, sizeof(struct power_event)); pwr->state = cpus_pstate_state[cpu]; pwr->start_time = cpus_pstate_start_times[cpu]; @@ -429,15 +423,13 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq) static void sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te) { - struct wake_event *we; struct per_pid *p; struct wakeup_entry *wake = (void *)te; + struct wake_event *we = zalloc(sizeof(*we)); - we = malloc(sizeof(struct wake_event)); if (!we) return; - memset(we, 0, sizeof(struct wake_event)); we->time = timestamp; we->waker = pid; @@ -491,11 +483,11 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te) } -static int process_sample_event(struct perf_tool *tool __used, - union perf_event *event __used, +static int process_sample_event(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_sample *sample, struct perf_evsel *evsel, - struct machine *machine __used) + struct machine *machine __maybe_unused) { struct trace_entry *te; @@ -579,13 +571,12 @@ static void end_sample_processing(void) struct power_event *pwr; for (cpu = 0; cpu <= numcpus; cpu++) { - pwr = malloc(sizeof(struct power_event)); + /* C state */ +#if 0 + pwr = zalloc(sizeof(*pwr)); if (!pwr) return; - memset(pwr, 0, sizeof(struct power_event)); - /* C state */ -#if 0 pwr->state = cpus_cstate_state[cpu]; pwr->start_time = cpus_cstate_start_times[cpu]; pwr->end_time = last_time; @@ -597,10 +588,9 @@ static void end_sample_processing(void) #endif /* P state */ - pwr = malloc(sizeof(struct power_event)); + pwr = zalloc(sizeof(*pwr)); if (!pwr) return; - memset(pwr, 0, sizeof(struct power_event)); pwr->state = cpus_pstate_state[cpu]; pwr->start_time = cpus_pstate_start_times[cpu]; @@ -830,11 +820,9 @@ static void draw_process_bars(void) static void add_process_filter(const char *string) { - struct process_filter *filt; - int pid; + int pid = strtoull(string, NULL, 10); + struct process_filter *filt = malloc(sizeof(*filt)); - pid = strtoull(string, NULL, 10); - filt = malloc(sizeof(struct process_filter)); if (!filt) return; @@ -1081,7 +1069,8 @@ static int __cmd_record(int argc, const char **argv) } static int -parse_process(const struct option *opt __used, const char *arg, int __used unset) +parse_process(const struct option *opt __maybe_unused, const char *arg, + int __maybe_unused unset) { if (arg) add_process_filter(arg); @@ -1106,7 +1095,8 @@ static const struct option options[] = { }; -int cmd_timechart(int argc, const char **argv, const char *prefix __used) +int cmd_timechart(int argc, const char **argv, + const char *prefix __maybe_unused) { argc = parse_options(argc, argv, options, timechart_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 68cd61ef6ac5..e434a16bb5ac 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -95,7 +95,8 @@ static void perf_top__update_print_entries(struct perf_top *top) top->print_entries -= 9; } -static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *arg) +static void perf_top__sig_winch(int sig __maybe_unused, + siginfo_t *info __maybe_unused, void *arg) { struct perf_top *top = arg; @@ -509,7 +510,7 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&counter, "Enter details event counter"); if (counter >= top->evlist->nr_entries) { - top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node); + top->sym_evsel = perf_evlist__first(top->evlist); fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel)); sleep(1); break; @@ -518,7 +519,7 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) if (top->sym_evsel->idx == counter) break; } else - top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node); + top->sym_evsel = perf_evlist__first(top->evlist); break; case 'f': prompt_integer(&top->count_filter, "Enter display event count filter"); @@ -663,7 +664,7 @@ static const char *skip_symbols[] = { NULL }; -static int symbol_filter(struct map *map __used, struct symbol *sym) +static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym) { const char *name = sym->name; int i; @@ -783,8 +784,10 @@ static void perf_event__process_sample(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, al.thread, - sample->callchain, &parent); + err = machine__resolve_callchain(machine, evsel, + al.thread, sample, + &parent); + if (err) return; } @@ -820,7 +823,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) int ret; while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) { - ret = perf_evlist__parse_sample(top->evlist, event, &sample, false); + ret = perf_evlist__parse_sample(top->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); continue; @@ -884,17 +887,14 @@ static void perf_top__mmap_read(struct perf_top *top) static void perf_top__start_counters(struct perf_top *top) { - struct perf_evsel *counter, *first; + struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; - first = list_entry(evlist->entries.next, struct perf_evsel, node); + if (top->group) + perf_evlist__set_leader(evlist); list_for_each_entry(counter, &evlist->entries, node) { struct perf_event_attr *attr = &counter->attr; - struct xyarray *group_fd = NULL; - - if (top->group && counter != first) - group_fd = first->fd; attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; @@ -925,8 +925,7 @@ retry_sample_id: attr->sample_id_all = top->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(counter, top->evlist->cpus, - top->evlist->threads, top->group, - group_fd) < 0) { + top->evlist->threads) < 0) { int err = errno; if (err == EPERM || err == EACCES) { @@ -1165,7 +1164,7 @@ static const char * const top_usage[] = { NULL }; -int cmd_top(int argc, const char **argv, const char *prefix __used) +int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_evsel *pos; int status; @@ -1328,7 +1327,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) pos->attr.sample_period = top.default_interval; } - top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node); + top.sym_evsel = perf_evlist__first(top.evlist); symbol_conf.priv_size = sizeof(struct annotation); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c new file mode 100644 index 000000000000..8f113dab8bf1 --- /dev/null +++ b/tools/perf/builtin-trace.c @@ -0,0 +1,310 @@ +#include "builtin.h" +#include "util/evlist.h" +#include "util/parse-options.h" +#include "util/thread_map.h" +#include "event-parse.h" + +#include <libaudit.h> +#include <stdlib.h> + +static struct syscall_fmt { + const char *name; + const char *alias; + bool errmsg; + bool timeout; +} syscall_fmts[] = { + { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, + { .name = "fstat", .errmsg = true, .alias = "newfstat", }, + { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, + { .name = "futex", .errmsg = true, }, + { .name = "poll", .errmsg = true, .timeout = true, }, + { .name = "ppoll", .errmsg = true, .timeout = true, }, + { .name = "read", .errmsg = true, }, + { .name = "recvfrom", .errmsg = true, }, + { .name = "select", .errmsg = true, .timeout = true, }, + { .name = "stat", .errmsg = true, .alias = "newstat", }, +}; + +static int syscall_fmt__cmp(const void *name, const void *fmtp) +{ + const struct syscall_fmt *fmt = fmtp; + return strcmp(name, fmt->name); +} + +static struct syscall_fmt *syscall_fmt__find(const char *name) +{ + const int nmemb = ARRAY_SIZE(syscall_fmts); + return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp); +} + +struct syscall { + struct event_format *tp_format; + const char *name; + struct syscall_fmt *fmt; +}; + +struct trace { + int audit_machine; + struct { + int max; + struct syscall *table; + } syscalls; + struct perf_record_opts opts; +}; + +static int trace__read_syscall_info(struct trace *trace, int id) +{ + char tp_name[128]; + struct syscall *sc; + + if (id > trace->syscalls.max) { + struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc)); + + if (nsyscalls == NULL) + return -1; + + if (trace->syscalls.max != -1) { + memset(nsyscalls + trace->syscalls.max + 1, 0, + (id - trace->syscalls.max) * sizeof(*sc)); + } else { + memset(nsyscalls, 0, (id + 1) * sizeof(*sc)); + } + + trace->syscalls.table = nsyscalls; + trace->syscalls.max = id; + } + + sc = trace->syscalls.table + id; + sc->name = audit_syscall_to_name(id, trace->audit_machine); + if (sc->name == NULL) + return -1; + + sc->fmt = syscall_fmt__find(sc->name); + + snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name); + sc->tp_format = event_format__new("syscalls", tp_name); + + if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) { + snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias); + sc->tp_format = event_format__new("syscalls", tp_name); + } + + return sc->tp_format != NULL ? 0 : -1; +} + +static size_t syscall__fprintf_args(struct syscall *sc, unsigned long *args, FILE *fp) +{ + int i = 0; + size_t printed = 0; + + if (sc->tp_format != NULL) { + struct format_field *field; + + for (field = sc->tp_format->format.fields->next; field; field = field->next) { + printed += fprintf(fp, "%s%s: %ld", printed ? ", " : "", + field->name, args[i++]); + } + } else { + while (i < 6) { + printed += fprintf(fp, "%sarg%d: %ld", printed ? ", " : "", i, args[i]); + ++i; + } + } + + return printed; +} + +static int trace__run(struct trace *trace) +{ + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evsel *evsel, *evsel_enter, *evsel_exit; + int err = -1, i, nr_events = 0, before; + + if (evlist == NULL) { + printf("Not enough memory to run!\n"); + goto out; + } + + evsel_enter = perf_evsel__newtp("raw_syscalls", "sys_enter", 0); + if (evsel_enter == NULL) { + printf("Couldn't read the raw_syscalls:sys_enter tracepoint information!\n"); + goto out_delete_evlist; + } + + perf_evlist__add(evlist, evsel_enter); + + evsel_exit = perf_evsel__newtp("raw_syscalls", "sys_exit", 1); + if (evsel_exit == NULL) { + printf("Couldn't read the raw_syscalls:sys_exit tracepoint information!\n"); + goto out_delete_evlist; + } + + perf_evlist__add(evlist, evsel_exit); + + err = perf_evlist__create_maps(evlist, &trace->opts.target); + if (err < 0) { + printf("Problems parsing the target to trace, check your options!\n"); + goto out_delete_evlist; + } + + perf_evlist__config_attrs(evlist, &trace->opts); + + err = perf_evlist__open(evlist); + if (err < 0) { + printf("Couldn't create the events: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + err = perf_evlist__mmap(evlist, UINT_MAX, false); + if (err < 0) { + printf("Couldn't mmap the events: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + perf_evlist__enable(evlist); +again: + before = nr_events; + + for (i = 0; i < evlist->nr_mmaps; i++) { + union perf_event *event; + + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + const u32 type = event->header.type; + struct syscall *sc; + struct perf_sample sample; + int id; + + ++nr_events; + + switch (type) { + case PERF_RECORD_SAMPLE: + break; + case PERF_RECORD_LOST: + printf("LOST %" PRIu64 " events!\n", event->lost.lost); + continue; + default: + printf("Unexpected %s event, skipping...\n", + perf_event__name(type)); + continue; + } + + err = perf_evlist__parse_sample(evlist, event, &sample); + if (err) { + printf("Can't parse sample, err = %d, skipping...\n", err); + continue; + } + + evsel = perf_evlist__id2evsel(evlist, sample.id); + if (evsel == NULL) { + printf("Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); + continue; + } + + id = perf_evsel__intval(evsel, &sample, "id"); + if (id < 0) { + printf("Invalid syscall %d id, skipping...\n", id); + continue; + } + + if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) && + trace__read_syscall_info(trace, id)) + continue; + + if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL)) + continue; + + sc = &trace->syscalls.table[id]; + + if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1) + printf("%d ", sample.tid); + + if (evsel == evsel_enter) { + void *args = perf_evsel__rawptr(evsel, &sample, "args"); + + printf("%s(", sc->name); + syscall__fprintf_args(sc, args, stdout); + } else if (evsel == evsel_exit) { + int ret = perf_evsel__intval(evsel, &sample, "ret"); + + if (ret < 0 && sc->fmt && sc->fmt->errmsg) { + char bf[256]; + const char *emsg = strerror_r(-ret, bf, sizeof(bf)), + *e = audit_errno_to_name(-ret); + + printf(") = -1 %s %s", e, emsg); + } else if (ret == 0 && sc->fmt && sc->fmt->timeout) + printf(") = 0 Timeout"); + else + printf(") = %d", ret); + + putchar('\n'); + } + } + } + + if (nr_events == before) + poll(evlist->pollfd, evlist->nr_fds, -1); + + goto again; + +out_delete_evlist: + perf_evlist__delete(evlist); +out: + return err; +} + +int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) +{ + const char * const trace_usage[] = { + "perf trace [<options>]", + NULL + }; + struct trace trace = { + .audit_machine = audit_detect_machine(), + .syscalls = { + . max = -1, + }, + .opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .no_delay = true, + .mmap_pages = 1024, + }, + }; + const struct option trace_options[] = { + OPT_STRING('p', "pid", &trace.opts.target.pid, "pid", + "trace events on existing process id"), + OPT_STRING(0, "tid", &trace.opts.target.tid, "tid", + "trace events on existing thread id"), + OPT_BOOLEAN(0, "all-cpus", &trace.opts.target.system_wide, + "system-wide collection from all CPUs"), + OPT_STRING(0, "cpu", &trace.opts.target.cpu_list, "cpu", + "list of cpus to monitor"), + OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit, + "child tasks do not inherit counters"), + OPT_UINTEGER(0, "mmap-pages", &trace.opts.mmap_pages, + "number of mmap data pages"), + OPT_STRING(0, "uid", &trace.opts.target.uid_str, "user", + "user to profile"), + OPT_END() + }; + int err; + + argc = parse_options(argc, argv, trace_options, trace_usage, 0); + if (argc) + usage_with_options(trace_usage, trace_options); + + err = perf_target__parse_uid(&trace.opts.target); + if (err) { + char bf[BUFSIZ]; + perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); + printf("%s", bf); + return err; + } + + return trace__run(&trace); +} diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index b382bd551aac..08143bd854c7 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -34,6 +34,8 @@ extern int cmd_kmem(int argc, const char **argv, const char *prefix); extern int cmd_lock(int argc, const char **argv, const char *prefix); extern int cmd_kvm(int argc, const char **argv, const char *prefix); extern int cmd_test(int argc, const char **argv, const char *prefix); +extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_inject(int argc, const char **argv, const char *prefix); +extern int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index d695fe40fbff..3e86bbd8c2d5 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -17,8 +17,9 @@ perf-report mainporcelain common perf-stat mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common +perf-trace mainporcelain common perf-script mainporcelain common -perf-probe mainporcelain common +perf-probe mainporcelain full perf-kmem mainporcelain common perf-lock mainporcelain common perf-kvm mainporcelain common diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 6c18785a6417..4add41bb0c7e 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -154,3 +154,53 @@ int main(void) return 0; } endef + +ifndef NO_LIBUNWIND +define SOURCE_LIBUNWIND +#include <libunwind.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +int main(void) +{ + unw_addr_space_t addr_space; + addr_space = unw_create_addr_space(NULL, 0); + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + return 0; +} +endef +endif + +ifndef NO_BACKTRACE +define SOURCE_BACKTRACE +#include <execinfo.h> +#include <stdio.h> + +int main(void) +{ + backtrace(NULL, 0); + backtrace_symbols(NULL, 0); + return 0; +} +endef +endif + +ifndef NO_LIBAUDIT +define SOURCE_LIBAUDIT +#include <libaudit.h> + +int main(void) +{ + return audit_open(); +} +endef +endif
\ No newline at end of file diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh index 95b6f8b6177a..e91930620269 100644 --- a/tools/perf/perf-archive.sh +++ b/tools/perf/perf-archive.sh @@ -24,7 +24,7 @@ NOBUILDID=0000000000000000000000000000000000000000 perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS if [ ! -s $BUILDIDS ] ; then echo "perf archive: no build-ids found" - rm -f $BUILDIDS + rm $BUILDIDS || true exit 1 fi @@ -39,8 +39,8 @@ while read build_id ; do echo ${filename#$PERF_BUILDID_LINKDIR} >> $MANIFEST done -tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST -rm -f $MANIFEST $BUILDIDS +tar cjf $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST +rm $MANIFEST $BUILDIDS || true echo -e "Now please run:\n" echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n" echo "wherever you need to run 'perf report' on." diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2b2e225a4d4c..fc2f770e3027 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -14,6 +14,7 @@ #include "util/run-command.h" #include "util/parse-events.h" #include "util/debugfs.h" +#include <pthread.h> const char perf_usage_string[] = "perf [--version] [--help] COMMAND [ARGS]"; @@ -24,6 +25,42 @@ const char perf_more_info_string[] = int use_browser = -1; static int use_pager = -1; +struct cmd_struct { + const char *cmd; + int (*fn)(int, const char **, const char *); + int option; +}; + +static struct cmd_struct commands[] = { + { "buildid-cache", cmd_buildid_cache, 0 }, + { "buildid-list", cmd_buildid_list, 0 }, + { "diff", cmd_diff, 0 }, + { "evlist", cmd_evlist, 0 }, + { "help", cmd_help, 0 }, + { "list", cmd_list, 0 }, + { "record", cmd_record, 0 }, + { "report", cmd_report, 0 }, + { "bench", cmd_bench, 0 }, + { "stat", cmd_stat, 0 }, + { "timechart", cmd_timechart, 0 }, + { "top", cmd_top, 0 }, + { "annotate", cmd_annotate, 0 }, + { "version", cmd_version, 0 }, + { "script", cmd_script, 0 }, + { "sched", cmd_sched, 0 }, +#ifndef NO_LIBELF_SUPPORT + { "probe", cmd_probe, 0 }, +#endif + { "kmem", cmd_kmem, 0 }, + { "lock", cmd_lock, 0 }, + { "kvm", cmd_kvm, 0 }, + { "test", cmd_test, 0 }, +#ifndef NO_LIBAUDIT_SUPPORT + { "trace", cmd_trace, 0 }, +#endif + { "inject", cmd_inject, 0 }, +}; + struct pager_config { const char *cmd; int val; @@ -160,6 +197,14 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) fprintf(stderr, "dir: %s\n", debugfs_mountpoint); if (envchanged) *envchanged = 1; + } else if (!strcmp(cmd, "--list-cmds")) { + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(commands); i++) { + struct cmd_struct *p = commands+i; + printf("%s ", p->cmd); + } + exit(0); } else { fprintf(stderr, "Unknown option: %s\n", cmd); usage(perf_usage_string); @@ -245,12 +290,6 @@ const char perf_version_string[] = PERF_VERSION; */ #define NEED_WORK_TREE (1<<2) -struct cmd_struct { - const char *cmd; - int (*fn)(int, const char **, const char *); - int option; -}; - static int run_builtin(struct cmd_struct *p, int argc, const char **argv) { int status; @@ -296,30 +335,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) static void handle_internal_command(int argc, const char **argv) { const char *cmd = argv[0]; - static struct cmd_struct commands[] = { - { "buildid-cache", cmd_buildid_cache, 0 }, - { "buildid-list", cmd_buildid_list, 0 }, - { "diff", cmd_diff, 0 }, - { "evlist", cmd_evlist, 0 }, - { "help", cmd_help, 0 }, - { "list", cmd_list, 0 }, - { "record", cmd_record, 0 }, - { "report", cmd_report, 0 }, - { "bench", cmd_bench, 0 }, - { "stat", cmd_stat, 0 }, - { "timechart", cmd_timechart, 0 }, - { "top", cmd_top, 0 }, - { "annotate", cmd_annotate, 0 }, - { "version", cmd_version, 0 }, - { "script", cmd_script, 0 }, - { "sched", cmd_sched, 0 }, - { "probe", cmd_probe, 0 }, - { "kmem", cmd_kmem, 0 }, - { "lock", cmd_lock, 0 }, - { "kvm", cmd_kvm, 0 }, - { "test", cmd_test, 0 }, - { "inject", cmd_inject, 0 }, - }; unsigned int i; static const char ext[] = STRIP_EXTENSION; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index f960ccb2edc6..87f4ec6d1f36 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -209,9 +209,15 @@ void pthread__unblock_sigwinch(void); #include "util/target.h" +enum perf_call_graph_mode { + CALLCHAIN_NONE, + CALLCHAIN_FP, + CALLCHAIN_DWARF +}; + struct perf_record_opts { struct perf_target target; - bool call_graph; + int call_graph; bool group; bool inherit_stat; bool no_delay; @@ -230,6 +236,7 @@ struct perf_record_opts { u64 branch_stack; u64 default_interval; u64 user_interval; + u16 stack_dump_size; }; #endif diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py new file mode 100755 index 000000000000..9e0985794e20 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py @@ -0,0 +1,94 @@ +# EventClass.py +# +# This is a library defining some events types classes, which could +# be used by other scripts to analyzing the perf samples. +# +# Currently there are just a few classes defined for examples, +# PerfEvent is the base class for all perf event sample, PebsEvent +# is a HW base Intel x86 PEBS event, and user could add more SW/HW +# event classes based on requirements. + +import struct + +# Event types, user could add more here +EVTYPE_GENERIC = 0 +EVTYPE_PEBS = 1 # Basic PEBS event +EVTYPE_PEBS_LL = 2 # PEBS event with load latency info +EVTYPE_IBS = 3 + +# +# Currently we don't have good way to tell the event type, but by +# the size of raw buffer, raw PEBS event with load latency data's +# size is 176 bytes, while the pure PEBS event's size is 144 bytes. +# +def create_event(name, comm, dso, symbol, raw_buf): + if (len(raw_buf) == 144): + event = PebsEvent(name, comm, dso, symbol, raw_buf) + elif (len(raw_buf) == 176): + event = PebsNHM(name, comm, dso, symbol, raw_buf) + else: + event = PerfEvent(name, comm, dso, symbol, raw_buf) + + return event + +class PerfEvent(object): + event_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_GENERIC): + self.name = name + self.comm = comm + self.dso = dso + self.symbol = symbol + self.raw_buf = raw_buf + self.ev_type = ev_type + PerfEvent.event_num += 1 + + def show(self): + print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso) + +# +# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer +# contains the context info when that event happened: the EFLAGS and +# linear IP info, as well as all the registers. +# +class PebsEvent(PerfEvent): + pebs_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS): + tmp_buf=raw_buf[0:80] + flags, ip, ax, bx, cx, dx, si, di, bp, sp = struct.unpack('QQQQQQQQQQ', tmp_buf) + self.flags = flags + self.ip = ip + self.ax = ax + self.bx = bx + self.cx = cx + self.dx = dx + self.si = si + self.di = di + self.bp = bp + self.sp = sp + + PerfEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type) + PebsEvent.pebs_num += 1 + del tmp_buf + +# +# Intel Nehalem and Westmere support PEBS plus Load Latency info which lie +# in the four 64 bit words write after the PEBS data: +# Status: records the IA32_PERF_GLOBAL_STATUS register value +# DLA: Data Linear Address (EIP) +# DSE: Data Source Encoding, where the latency happens, hit or miss +# in L1/L2/L3 or IO operations +# LAT: the actual latency in cycles +# +class PebsNHM(PebsEvent): + pebs_nhm_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS_LL): + tmp_buf=raw_buf[144:176] + status, dla, dse, lat = struct.unpack('QQQQ', tmp_buf) + self.status = status + self.dla = dla + self.dse = dse + self.lat = lat + + PebsEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type) + PebsNHM.pebs_nhm_num += 1 + del tmp_buf diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-record b/tools/perf/scripts/python/bin/event_analyzing_sample-record new file mode 100644 index 000000000000..5ce652dabd02 --- /dev/null +++ b/tools/perf/scripts/python/bin/event_analyzing_sample-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# event_analyzing_sample.py can cover all type of perf samples including +# the tracepoints, so no special record requirements, just record what +# you want to analyze. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-report b/tools/perf/scripts/python/bin/event_analyzing_sample-report new file mode 100644 index 000000000000..0941fc94e158 --- /dev/null +++ b/tools/perf/scripts/python/bin/event_analyzing_sample-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: analyze all perf samples +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py new file mode 100644 index 000000000000..163c39fa12d9 --- /dev/null +++ b/tools/perf/scripts/python/event_analyzing_sample.py @@ -0,0 +1,189 @@ +# event_analyzing_sample.py: general event handler in python +# +# Current perf report is already very powerful with the annotation integrated, +# and this script is not trying to be as powerful as perf report, but +# providing end user/developer a flexible way to analyze the events other +# than trace points. +# +# The 2 database related functions in this script just show how to gather +# the basic information, and users can modify and write their own functions +# according to their specific requirement. +# +# The first function "show_general_events" just does a basic grouping for all +# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is +# for a x86 HW PMU event: PEBS with load latency data. +# + +import os +import sys +import math +import struct +import sqlite3 + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from EventClass import * + +# +# If the perf.data has a big number of samples, then the insert operation +# will be very time consuming (about 10+ minutes for 10000 samples) if the +# .db database is on disk. Move the .db file to RAM based FS to speedup +# the handling, which will cut the time down to several seconds. +# +con = sqlite3.connect("/dev/shm/perf.db") +con.isolation_level = None + +def trace_begin(): + print "In trace_begin:\n" + + # + # Will create several tables at the start, pebs_ll is for PEBS data with + # load latency info, while gen_events is for general event. + # + con.execute(""" + create table if not exists gen_events ( + name text, + symbol text, + comm text, + dso text + );""") + con.execute(""" + create table if not exists pebs_ll ( + name text, + symbol text, + comm text, + dso text, + flags integer, + ip integer, + status integer, + dse integer, + dla integer, + lat integer + );""") + +# +# Create and insert event object to a database so that user could +# do more analysis with simple database commands. +# +def process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + + # Symbol and dso info are not always resolved + if (param_dict.has_key("dso")): + dso = param_dict["dso"] + else: + dso = "Unknown_dso" + + if (param_dict.has_key("symbol")): + symbol = param_dict["symbol"] + else: + symbol = "Unknown_symbol" + + # Create the event object and insert it to the right table in database + event = create_event(name, comm, dso, symbol, raw_buf) + insert_db(event) + +def insert_db(event): + if event.ev_type == EVTYPE_GENERIC: + con.execute("insert into gen_events values(?, ?, ?, ?)", + (event.name, event.symbol, event.comm, event.dso)) + elif event.ev_type == EVTYPE_PEBS_LL: + event.ip &= 0x7fffffffffffffff + event.dla &= 0x7fffffffffffffff + con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", + (event.name, event.symbol, event.comm, event.dso, event.flags, + event.ip, event.status, event.dse, event.dla, event.lat)) + +def trace_end(): + print "In trace_end:\n" + # We show the basic info for the 2 type of event classes + show_general_events() + show_pebs_ll() + con.close() + +# +# As the event number may be very big, so we can't use linear way +# to show the histogram in real number, but use a log2 algorithm. +# + +def num2sym(num): + # Each number will have at least one '#' + snum = '#' * (int)(math.log(num, 2) + 1) + return snum + +def show_general_events(): + + # Check the total record number in the table + count = con.execute("select count(*) from gen_events") + for t in count: + print "There is %d records in gen_events table" % t[0] + if t[0] == 0: + return + + print "Statistics about the general events grouped by thread/symbol/dso: \n" + + # Group by thread + commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)") + print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42) + for row in commq: + print "%16s %8d %s" % (row[0], row[1], num2sym(row[1])) + + # Group by symbol + print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58) + symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)") + for row in symbolq: + print "%32s %8d %s" % (row[0], row[1], num2sym(row[1])) + + # Group by dso + print "\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74) + dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)") + for row in dsoq: + print "%40s %8d %s" % (row[0], row[1], num2sym(row[1])) + +# +# This function just shows the basic info, and we could do more with the +# data in the tables, like checking the function parameters when some +# big latency events happen. +# +def show_pebs_ll(): + + count = con.execute("select count(*) from pebs_ll") + for t in count: + print "There is %d records in pebs_ll table" % t[0] + if t[0] == 0: + return + + print "Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n" + + # Group by thread + commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)") + print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42) + for row in commq: + print "%16s %8d %s" % (row[0], row[1], num2sym(row[1])) + + # Group by symbol + print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58) + symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)") + for row in symbolq: + print "%32s %8d %s" % (row[0], row[1], num2sym(row[1])) + + # Group by dse + dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)") + print "\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58) + for row in dseq: + print "%32s %8d %s" % (row[0], row[1], num2sym(row[1])) + + # Group by latency + latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat") + print "\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58) + for row in latq: + print "%32s %8d %s" % (row[0], row[1], num2sym(row[1])) + +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 1818a531f1d3..4aeb7d5df939 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -269,7 +269,7 @@ int ui_browser__show(struct ui_browser *browser, const char *title, return err ? 0 : -1; } -void ui_browser__hide(struct ui_browser *browser __used) +void ui_browser__hide(struct ui_browser *browser __maybe_unused) { pthread_mutex_lock(&ui__lock); ui_helpline__pop(); @@ -518,7 +518,7 @@ static struct ui_browser__colorset { static int ui_browser__color_config(const char *var, const char *value, - void *data __used) + void *data __maybe_unused) { char *fg = NULL, *bg; int i; @@ -602,7 +602,8 @@ void __ui_browser__vline(struct ui_browser *browser, unsigned int column, SLsmg_set_char_set(0); } -void ui_browser__write_graph(struct ui_browser *browser __used, int graph) +void ui_browser__write_graph(struct ui_browser *browser __maybe_unused, + int graph) { SLsmg_set_char_set(1); SLsmg_write_char(graph); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 67a2703e666a..8f8cd2d73b3b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -54,7 +54,8 @@ static inline struct browser_disasm_line *disasm_line__browser(struct disasm_lin return (struct browser_disasm_line *)(dl + 1); } -static bool disasm_line__filter(struct ui_browser *browser __used, void *entry) +static bool disasm_line__filter(struct ui_browser *browser __maybe_unused, + void *entry) { if (annotate_browser__opts.hide_src_code) { struct disasm_line *dl = list_entry(entry, struct disasm_line, node); @@ -928,7 +929,8 @@ static int annotate_config__cmp(const void *name, const void *cfgp) return strcmp(name, cfg->name); } -static int annotate__config(const char *var, const char *value, void *data __used) +static int annotate__config(const char *var, const char *value, + void *data __maybe_unused) { struct annotate__config *cfg; const char *name; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 413bd62eedb1..a21f40bebbac 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -24,9 +24,12 @@ struct hist_browser { struct hist_entry *he_selection; struct map_symbol *selection; int print_seq; + bool show_dso; bool has_symbols; }; +extern void hist_browser__init_hpp(void); + static int hists__browser_title(struct hists *hists, char *bf, size_t size, const char *ev_name); @@ -376,12 +379,19 @@ out: } static char *callchain_list__sym_name(struct callchain_list *cl, - char *bf, size_t bfsize) + char *bf, size_t bfsize, bool show_dso) { + int printed; + if (cl->ms.sym) - return cl->ms.sym->name; + printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name); + else + printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); + + if (show_dso) + scnprintf(bf + printed, bfsize - printed, " %s", + cl->ms.map ? cl->ms.map->dso->short_name : "unknown"); - snprintf(bf, bfsize, "%#" PRIx64, cl->ip); return bf; } @@ -417,7 +427,7 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse remaining -= cumul; list_for_each_entry(chain, &child->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; + char bf[1024], *alloc_str; const char *str; int color; bool was_first = first; @@ -434,7 +444,8 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse } alloc_str = NULL; - str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + str = callchain_list__sym_name(chain, bf, sizeof(bf), + browser->show_dso); if (was_first) { double percent = cumul * 100.0 / new_total; @@ -493,7 +504,7 @@ static int hist_browser__show_callchain_node(struct hist_browser *browser, char folded_sign = ' '; list_for_each_entry(chain, &node->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *s; + char bf[1024], *s; int color; folded_sign = callchain_list__folded(chain); @@ -510,7 +521,8 @@ static int hist_browser__show_callchain_node(struct hist_browser *browser, *is_current_entry = true; } - s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + s = callchain_list__sym_name(chain, bf, sizeof(bf), + browser->show_dso); ui_browser__gotorc(&browser->b, row, 0); ui_browser__set_color(&browser->b, color); slsmg_write_nstring(" ", offset); @@ -553,14 +565,47 @@ static int hist_browser__show_callchain(struct hist_browser *browser, return row - first_row; } +#define HPP__COLOR_FN(_name, _field) \ +static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + double percent = 100.0 * he->_field / hpp->total_period; \ + *(double *)hpp->ptr = percent; \ + return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); \ +} + +HPP__COLOR_FN(overhead, period) +HPP__COLOR_FN(overhead_sys, period_sys) +HPP__COLOR_FN(overhead_us, period_us) +HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) +HPP__COLOR_FN(overhead_guest_us, period_guest_us) + +#undef HPP__COLOR_FN + +void hist_browser__init_hpp(void) +{ + perf_hpp__init(false, false); + + perf_hpp__format[PERF_HPP__OVERHEAD].color = + hist_browser__hpp_color_overhead; + perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = + hist_browser__hpp_color_overhead_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_US].color = + hist_browser__hpp_color_overhead_us; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = + hist_browser__hpp_color_overhead_guest_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = + hist_browser__hpp_color_overhead_guest_us; +} + static int hist_browser__show_entry(struct hist_browser *browser, struct hist_entry *entry, unsigned short row) { char s[256]; double percent; - int printed = 0; - int width = browser->b.width - 6; /* The percentage */ + int i, printed = 0; + int width = browser->b.width; char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&browser->b, row); off_t row_offset = entry->row_offset; @@ -576,35 +621,50 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (row_offset == 0) { - hist_entry__snprintf(entry, s, sizeof(s), browser->hists); - percent = (entry->period * 100.0) / browser->hists->stats.total_period; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .total_period = browser->hists->stats.total_period, + }; - ui_browser__set_percent_color(&browser->b, percent, current_entry); ui_browser__gotorc(&browser->b, row, 0); - if (symbol_conf.use_callchain) { - slsmg_printf("%c ", folded_sign); - width -= 2; - } - slsmg_printf(" %5.2f%%", percent); + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; - /* The scroll bar isn't being used */ - if (!browser->b.navkeypressed) - width += 1; + if (i) { + slsmg_printf(" "); + width -= 2; + } - if (!current_entry || !browser->b.navkeypressed) - ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + if (perf_hpp__format[i].color) { + hpp.ptr = &percent; + /* It will set percent for us. See HPP__COLOR_FN above. */ + width -= perf_hpp__format[i].color(&hpp, entry); - if (symbol_conf.show_nr_samples) { - slsmg_printf(" %11u", entry->nr_events); - width -= 12; - } + ui_browser__set_percent_color(&browser->b, percent, current_entry); + + if (i == 0 && symbol_conf.use_callchain) { + slsmg_printf("%c ", folded_sign); + width -= 2; + } + + slsmg_printf("%s", s); - if (symbol_conf.show_total_period) { - slsmg_printf(" %12" PRIu64, entry->period); - width -= 13; + if (!current_entry || !browser->b.navkeypressed) + ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + } else { + width -= perf_hpp__format[i].entry(&hpp, entry); + slsmg_printf("%s", s); + } } + /* The scroll bar isn't being used */ + if (!browser->b.navkeypressed) + width += 1; + + hist_entry__sort_snprintf(entry, s, sizeof(s), browser->hists); slsmg_write_nstring(s, width); ++row; ++printed; @@ -830,7 +890,7 @@ static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *bro remaining -= cumul; list_for_each_entry(chain, &child->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; + char bf[1024], *alloc_str; const char *str; bool was_first = first; @@ -842,7 +902,8 @@ static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *bro folded_sign = callchain_list__folded(chain); alloc_str = NULL; - str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + str = callchain_list__sym_name(chain, bf, sizeof(bf), + browser->show_dso); if (was_first) { double percent = cumul * 100.0 / new_total; @@ -880,10 +941,10 @@ static int hist_browser__fprintf_callchain_node(struct hist_browser *browser, int printed = 0; list_for_each_entry(chain, &node->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *s; + char bf[1024], *s; folded_sign = callchain_list__folded(chain); - s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso); printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s); } @@ -920,7 +981,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, if (symbol_conf.use_callchain) folded_sign = hist_entry__folded(he); - hist_entry__snprintf(he, s, sizeof(s), browser->hists); + hist_entry__sort_snprintf(he, s, sizeof(s), browser->hists); percent = (he->period * 100.0) / browser->hists->stats.total_period; if (symbol_conf.use_callchain) @@ -1133,6 +1194,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; case 'd': goto zoom_dso; + case 'V': + browser->show_dso = !browser->show_dso; + continue; case 't': goto zoom_thread; case '/': @@ -1164,6 +1228,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "d Zoom into current DSO\n" "t Zoom into current Thread\n" "P Print histograms to perf.hist.N\n" + "V Verbose (DSO names in callchains, etc)\n" "/ Filter symbol by name"); continue; case K_ENTER: diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index ec12e0b4ded6..7ff99ec1d95e 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -3,6 +3,7 @@ #include "../evsel.h" #include "../sort.h" #include "../hist.h" +#include "../helpline.h" #include "gtk.h" #include <signal.h> @@ -35,6 +36,57 @@ static void perf_gtk__resize_window(GtkWidget *window) gtk_window_resize(GTK_WINDOW(window), width, height); } +static const char *perf_gtk__get_percent_color(double percent) +{ + if (percent >= MIN_RED) + return "<span fgcolor='red'>"; + if (percent >= MIN_GREEN) + return "<span fgcolor='dark green'>"; + return NULL; +} + +#define HPP__COLOR_FN(_name, _field) \ +static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + double percent = 100.0 * he->_field / hpp->total_period; \ + const char *markup; \ + int ret = 0; \ + \ + markup = perf_gtk__get_percent_color(percent); \ + if (markup) \ + ret += scnprintf(hpp->buf, hpp->size, "%s", markup); \ + ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); \ + if (markup) \ + ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); \ + \ + return ret; \ +} + +HPP__COLOR_FN(overhead, period) +HPP__COLOR_FN(overhead_sys, period_sys) +HPP__COLOR_FN(overhead_us, period_us) +HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) +HPP__COLOR_FN(overhead_guest_us, period_guest_us) + +#undef HPP__COLOR_FN + +void perf_gtk__init_hpp(void) +{ + perf_hpp__init(false, false); + + perf_hpp__format[PERF_HPP__OVERHEAD].color = + perf_gtk__hpp_color_overhead; + perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = + perf_gtk__hpp_color_overhead_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_US].color = + perf_gtk__hpp_color_overhead_us; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = + perf_gtk__hpp_color_overhead_guest_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = + perf_gtk__hpp_color_overhead_guest_us; +} + static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) { GType col_types[MAX_COLUMNS]; @@ -42,15 +94,25 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) struct sort_entry *se; GtkListStore *store; struct rb_node *nd; - u64 total_period; GtkWidget *view; - int col_idx; + int i, col_idx; int nr_cols; + char s[512]; + + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .total_period = hists->stats.total_period, + }; nr_cols = 0; - /* The percentage column */ - col_types[nr_cols++] = G_TYPE_STRING; + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; + + col_types[nr_cols++] = G_TYPE_STRING; + } list_for_each_entry(se, &hist_entry__sort_list, list) { if (se->elide) @@ -67,11 +129,17 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) col_idx = 0; - /* The percentage column */ - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, "Overhead (%)", - renderer, "text", - col_idx++, NULL); + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; + + perf_hpp__format[i].header(&hpp); + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, s, + renderer, "markup", + col_idx++, NULL); + } list_for_each_entry(se, &hist_entry__sort_list, list) { if (se->elide) @@ -87,13 +155,9 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) g_object_unref(GTK_TREE_MODEL(store)); - total_period = hists->stats.total_period; - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); GtkTreeIter iter; - double percent; - char s[512]; if (h->filtered) continue; @@ -102,11 +166,17 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) col_idx = 0; - percent = (h->period * 100.0) / total_period; + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; - snprintf(s, ARRAY_SIZE(s), "%.2f", percent); + if (perf_hpp__format[i].color) + perf_hpp__format[i].color(&hpp, h); + else + perf_hpp__format[i].entry(&hpp, h); - gtk_list_store_set(store, &iter, col_idx++, s, -1); + gtk_list_store_set(store, &iter, col_idx++, s, -1); + } list_for_each_entry(se, &hist_entry__sort_list, list) { if (se->elide) @@ -166,9 +236,10 @@ static GtkWidget *perf_gtk__setup_statusbar(void) } int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, - const char *help __used, - void (*timer) (void *arg)__used, - void *arg __used, int delay_secs __used) + const char *help, + void (*timer) (void *arg)__maybe_unused, + void *arg __maybe_unused, + int delay_secs __maybe_unused) { struct perf_evsel *pos; GtkWidget *vbox; @@ -233,6 +304,8 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); + ui_helpline__push(help); + gtk_main(); perf_gtk__deactivate_context(&pgctx); diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index a4d0f2b4a2dc..687af0bba187 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -29,6 +29,9 @@ static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx) struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window); int perf_gtk__deactivate_context(struct perf_gtk_context **ctx); +void perf_gtk__init_helpline(void); +void perf_gtk__init_hpp(void); + #ifndef HAVE_GTK_INFO_BAR static inline GtkWidget *perf_gtk__setup_info_bar(void) { diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c new file mode 100644 index 000000000000..5db4432ff12a --- /dev/null +++ b/tools/perf/ui/gtk/helpline.c @@ -0,0 +1,56 @@ +#include <stdio.h> +#include <string.h> + +#include "gtk.h" +#include "../ui.h" +#include "../helpline.h" +#include "../../util/debug.h" + +static void gtk_helpline_pop(void) +{ + if (!perf_gtk__is_active_context(pgctx)) + return; + + gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id); +} + +static void gtk_helpline_push(const char *msg) +{ + if (!perf_gtk__is_active_context(pgctx)) + return; + + gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id, msg); +} + +static struct ui_helpline gtk_helpline_fns = { + .pop = gtk_helpline_pop, + .push = gtk_helpline_push, +}; + +void perf_gtk__init_helpline(void) +{ + helpline_fns = >k_helpline_fns; +} + +int perf_gtk__show_helpline(const char *fmt, va_list ap) +{ + int ret; + char *ptr; + static int backlog; + + ret = vscnprintf(ui_helpline__current + backlog, + sizeof(ui_helpline__current) - backlog, fmt, ap); + backlog += ret; + + /* only first line can be displayed */ + ptr = strchr(ui_helpline__current, '\n'); + if (ptr && (ptr - ui_helpline__current) <= backlog) { + *ptr = '\0'; + ui_helpline__puts(ui_helpline__current); + backlog = 0; + } + + return ret; +} diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 92879ce61e2f..3c4c6ef78283 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -7,11 +7,15 @@ extern struct perf_error_ops perf_gtk_eops; int perf_gtk__init(void) { perf_error__register(&perf_gtk_eops); + perf_gtk__init_helpline(); + perf_gtk__init_hpp(); return gtk_init_check(NULL, NULL) ? 0 : -1; } -void perf_gtk__exit(bool wait_for_ok __used) +void perf_gtk__exit(bool wait_for_ok __maybe_unused) { + if (!perf_gtk__is_active_context(pgctx)) + return; perf_error__unregister(&perf_gtk_eops); gtk_main_quit(); } diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c index 0ead373c0dfb..8aada5b3c04c 100644 --- a/tools/perf/ui/gtk/util.c +++ b/tools/perf/ui/gtk/util.c @@ -117,13 +117,8 @@ struct perf_error_ops perf_gtk_eops = { * For now, just add stubs for NO_NEWT=1 build. */ #ifdef NO_NEWT_SUPPORT -int ui_helpline__show_help(const char *format __used, va_list ap __used) -{ - return 0; -} - -void ui_progress__update(u64 curr __used, u64 total __used, - const char *title __used) +void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused, + const char *title __maybe_unused) { } #endif diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c index 2f950c2641c8..a49bcf3c190b 100644 --- a/tools/perf/ui/helpline.c +++ b/tools/perf/ui/helpline.c @@ -5,23 +5,32 @@ #include "../debug.h" #include "helpline.h" #include "ui.h" -#include "libslang.h" -void ui_helpline__pop(void) +char ui_helpline__current[512]; + +static void nop_helpline__pop(void) { } -char ui_helpline__current[512]; +static void nop_helpline__push(const char *msg __maybe_unused) +{ +} -void ui_helpline__push(const char *msg) +static struct ui_helpline default_helpline_fns = { + .pop = nop_helpline__pop, + .push = nop_helpline__push, +}; + +struct ui_helpline *helpline_fns = &default_helpline_fns; + +void ui_helpline__pop(void) { - const size_t sz = sizeof(ui_helpline__current); + helpline_fns->pop(); +} - SLsmg_gotorc(SLtt_Screen_Rows - 1, 0); - SLsmg_set_color(0); - SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols); - SLsmg_refresh(); - strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; +void ui_helpline__push(const char *msg) +{ + helpline_fns->push(msg); } void ui_helpline__vpush(const char *fmt, va_list ap) @@ -50,30 +59,3 @@ void ui_helpline__puts(const char *msg) ui_helpline__pop(); ui_helpline__push(msg); } - -void ui_helpline__init(void) -{ - ui_helpline__puts(" "); -} - -char ui_helpline__last_msg[1024]; - -int ui_helpline__show_help(const char *format, va_list ap) -{ - int ret; - static int backlog; - - pthread_mutex_lock(&ui__lock); - ret = vscnprintf(ui_helpline__last_msg + backlog, - sizeof(ui_helpline__last_msg) - backlog, format, ap); - backlog += ret; - - if (ui_helpline__last_msg[backlog - 1] == '\n') { - ui_helpline__puts(ui_helpline__last_msg); - SLsmg_refresh(); - backlog = 0; - } - pthread_mutex_unlock(&ui__lock); - - return ret; -} diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h index 7bab6b34e35e..2b667ee454c3 100644 --- a/tools/perf/ui/helpline.h +++ b/tools/perf/ui/helpline.h @@ -4,13 +4,44 @@ #include <stdio.h> #include <stdarg.h> +#include "../util/cache.h" + +struct ui_helpline { + void (*pop)(void); + void (*push)(const char *msg); +}; + +extern struct ui_helpline *helpline_fns; + void ui_helpline__init(void); + void ui_helpline__pop(void); void ui_helpline__push(const char *msg); void ui_helpline__vpush(const char *fmt, va_list ap); void ui_helpline__fpush(const char *fmt, ...); void ui_helpline__puts(const char *msg); -extern char ui_helpline__current[]; +extern char ui_helpline__current[512]; + +#ifdef NO_NEWT_SUPPORT +static inline int ui_helpline__show_help(const char *format __maybe_unused, + va_list ap __maybe_unused) +{ + return 0; +} +#else +extern char ui_helpline__last_msg[]; +int ui_helpline__show_help(const char *format, va_list ap); +#endif /* NO_NEWT_SUPPORT */ + +#ifdef NO_GTK2_SUPPORT +static inline int perf_gtk__show_helpline(const char *format __maybe_unused, + va_list ap __maybe_unused) +{ + return 0; +} +#else +int perf_gtk__show_helpline(const char *format, va_list ap); +#endif /* NO_GTK2_SUPPORT */ #endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c new file mode 100644 index 000000000000..e3f8cd46e7d7 --- /dev/null +++ b/tools/perf/ui/hist.c @@ -0,0 +1,390 @@ +#include <math.h> + +#include "../util/hist.h" +#include "../util/util.h" +#include "../util/sort.h" + + +/* hist period print (hpp) functions */ +static int hpp__header_overhead(struct perf_hpp *hpp) +{ + const char *fmt = hpp->ptr ? "Baseline" : "Overhead"; + + return scnprintf(hpp->buf, hpp->size, fmt); +} + +static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused) +{ + return 8; +} + +static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period / hpp->total_period; + + if (hpp->ptr) { + struct hists *old_hists = hpp->ptr; + u64 total_period = old_hists->stats.total_period; + u64 base_period = he->pair ? he->pair->period : 0; + + if (total_period) + percent = 100.0 * base_period / total_period; + else + percent = 0.0; + } + + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); +} + +static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period / hpp->total_period; + const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; + + if (hpp->ptr) { + struct hists *old_hists = hpp->ptr; + u64 total_period = old_hists->stats.total_period; + u64 base_period = he->pair ? he->pair->period : 0; + + if (total_period) + percent = 100.0 * base_period / total_period; + else + percent = 0.0; + } + + return scnprintf(hpp->buf, hpp->size, fmt, percent); +} + +static int hpp__header_overhead_sys(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "sys"); +} + +static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused) +{ + return 7; +} + +static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period_sys / hpp->total_period; + return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); +} + +static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period_sys / hpp->total_period; + const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; + + return scnprintf(hpp->buf, hpp->size, fmt, percent); +} + +static int hpp__header_overhead_us(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "user"); +} + +static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused) +{ + return 7; +} + +static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period_us / hpp->total_period; + return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); +} + +static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = 100.0 * he->period_us / hpp->total_period; + const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; + + return scnprintf(hpp->buf, hpp->size, fmt, percent); +} + +static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp) +{ + return scnprintf(hpp->buf, hpp->size, "guest sys"); +} + +static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused) +{ + return 9; +} + +static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp, + struct hist_entry *he) +{ + double percent = 100.0 * he->period_guest_sys / hpp->total_period; + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); +} + +static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp, + struct hist_entry *he) +{ + double percent = 100.0 * he->period_guest_sys / hpp->total_period; + const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; + + return scnprintf(hpp->buf, hpp->size, fmt, percent); +} + +static int hpp__header_overhead_guest_us(struct perf_hpp *hpp) +{ + return scnprintf(hpp->buf, hpp->size, "guest usr"); +} + +static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused) +{ + return 9; +} + +static int hpp__color_overhead_guest_us(struct perf_hpp *hpp, + struct hist_entry *he) +{ + double percent = 100.0 * he->period_guest_us / hpp->total_period; + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); +} + +static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp, + struct hist_entry *he) +{ + double percent = 100.0 * he->period_guest_us / hpp->total_period; + const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; + + return scnprintf(hpp->buf, hpp->size, fmt, percent); +} + +static int hpp__header_samples(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%11s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Samples"); +} + +static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused) +{ + return 11; +} + +static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he) +{ + const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64; + + return scnprintf(hpp->buf, hpp->size, fmt, he->nr_events); +} + +static int hpp__header_period(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Period"); +} + +static int hpp__width_period(struct perf_hpp *hpp __maybe_unused) +{ + return 12; +} + +static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he) +{ + const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; + + return scnprintf(hpp->buf, hpp->size, fmt, he->period); +} + +static int hpp__header_delta(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Delta"); +} + +static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused) +{ + return 7; +} + +static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he) +{ + struct hists *pair_hists = hpp->ptr; + u64 old_total, new_total; + double old_percent = 0, new_percent = 0; + double diff; + const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s"; + char buf[32] = " "; + + old_total = pair_hists->stats.total_period; + if (old_total > 0 && he->pair) + old_percent = 100.0 * he->pair->period / old_total; + + new_total = hpp->total_period; + if (new_total > 0) + new_percent = 100.0 * he->period / new_total; + + diff = new_percent - old_percent; + if (fabs(diff) >= 0.01) + scnprintf(buf, sizeof(buf), "%+4.2F%%", diff); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +static int hpp__header_displ(struct perf_hpp *hpp) +{ + return scnprintf(hpp->buf, hpp->size, "Displ."); +} + +static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused) +{ + return 6; +} + +static int hpp__entry_displ(struct perf_hpp *hpp, + struct hist_entry *he __maybe_unused) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s"; + char buf[32] = " "; + + if (hpp->displacement) + scnprintf(buf, sizeof(buf), "%+4ld", hpp->displacement); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +#define HPP__COLOR_PRINT_FNS(_name) \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .color = hpp__color_ ## _name, \ + .entry = hpp__entry_ ## _name + +#define HPP__PRINT_FNS(_name) \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .entry = hpp__entry_ ## _name + +struct perf_hpp_fmt perf_hpp__format[] = { + { .cond = true, HPP__COLOR_PRINT_FNS(overhead) }, + { .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) }, + { .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) }, + { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_sys) }, + { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) }, + { .cond = false, HPP__PRINT_FNS(samples) }, + { .cond = false, HPP__PRINT_FNS(period) }, + { .cond = false, HPP__PRINT_FNS(delta) }, + { .cond = false, HPP__PRINT_FNS(displ) } +}; + +#undef HPP__COLOR_PRINT_FNS +#undef HPP__PRINT_FNS + +void perf_hpp__init(bool need_pair, bool show_displacement) +{ + if (symbol_conf.show_cpu_utilization) { + perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true; + perf_hpp__format[PERF_HPP__OVERHEAD_US].cond = true; + + if (perf_guest) { + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].cond = true; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].cond = true; + } + } + + if (symbol_conf.show_nr_samples) + perf_hpp__format[PERF_HPP__SAMPLES].cond = true; + + if (symbol_conf.show_total_period) + perf_hpp__format[PERF_HPP__PERIOD].cond = true; + + if (need_pair) { + perf_hpp__format[PERF_HPP__DELTA].cond = true; + + if (show_displacement) + perf_hpp__format[PERF_HPP__DISPL].cond = true; + } +} + +static inline void advance_hpp(struct perf_hpp *hpp, int inc) +{ + hpp->buf += inc; + hpp->size -= inc; +} + +int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, + bool color) +{ + const char *sep = symbol_conf.field_sep; + char *start = hpp->buf; + int i, ret; + + if (symbol_conf.exclude_other && !he->parent) + return 0; + + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; + + if (!sep || i > 0) { + ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); + advance_hpp(hpp, ret); + } + + if (color && perf_hpp__format[i].color) + ret = perf_hpp__format[i].color(hpp, he); + else + ret = perf_hpp__format[i].entry(hpp, he); + + advance_hpp(hpp, ret); + } + + return hpp->buf - start; +} + +int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, + struct hists *hists) +{ + const char *sep = symbol_conf.field_sep; + struct sort_entry *se; + int ret = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + ret += scnprintf(s + ret, size - ret, "%s", sep ?: " "); + ret += se->se_snprintf(he, s + ret, size - ret, + hists__col_len(hists, se->se_width_idx)); + } + + return ret; +} + +/* + * See hists__fprintf to match the column widths + */ +unsigned int hists__sort_list_width(struct hists *hists) +{ + struct sort_entry *se; + int i, ret = 0; + + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + if (!perf_hpp__format[i].cond) + continue; + if (i) + ret += 2; + + ret += perf_hpp__format[i].width(NULL); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) + if (!se->elide) + ret += 2 + hists__col_len(hists, se->se_width_idx); + + if (verbose) /* Addr + origin */ + ret += 3 + BITS_PER_LONG / 4; + + return ret; +} diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 791fb15ce350..bd7d460f844c 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -1,6 +1,10 @@ -#include "../cache.h" -#include "../debug.h" +#include <pthread.h> +#include "../util/cache.h" +#include "../util/debug.h" +#include "../util/hist.h" + +pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void setup_browser(bool fallback_to_pager) { @@ -25,6 +29,8 @@ void setup_browser(bool fallback_to_pager) use_browser = 0; if (fallback_to_pager) setup_pager(); + + perf_hpp__init(false, false); break; } } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c new file mode 100644 index 000000000000..882461a42830 --- /dev/null +++ b/tools/perf/ui/stdio/hist.c @@ -0,0 +1,498 @@ +#include <stdio.h> + +#include "../../util/util.h" +#include "../../util/hist.h" +#include "../../util/sort.h" + + +static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) +{ + int i; + int ret = fprintf(fp, " "); + + for (i = 0; i < left_margin; i++) + ret += fprintf(fp, " "); + + return ret; +} + +static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, + int left_margin) +{ + int i; + size_t ret = callchain__fprintf_left_margin(fp, left_margin); + + for (i = 0; i < depth; i++) + if (depth_mask & (1 << i)) + ret += fprintf(fp, "| "); + else + ret += fprintf(fp, " "); + + ret += fprintf(fp, "\n"); + + return ret; +} + +static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, + int depth, int depth_mask, int period, + u64 total_samples, u64 hits, + int left_margin) +{ + int i; + size_t ret = 0; + + ret += callchain__fprintf_left_margin(fp, left_margin); + for (i = 0; i < depth; i++) { + if (depth_mask & (1 << i)) + ret += fprintf(fp, "|"); + else + ret += fprintf(fp, " "); + if (!period && i == depth - 1) { + double percent; + + percent = hits * 100.0 / total_samples; + ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent); + } else + ret += fprintf(fp, "%s", " "); + } + if (chain->ms.sym) + ret += fprintf(fp, "%s\n", chain->ms.sym->name); + else + ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip); + + return ret; +} + +static struct symbol *rem_sq_bracket; +static struct callchain_list rem_hits; + +static void init_rem_hits(void) +{ + rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6); + if (!rem_sq_bracket) { + fprintf(stderr, "Not enough memory to display remaining hits\n"); + return; + } + + strcpy(rem_sq_bracket->name, "[...]"); + rem_hits.ms.sym = rem_sq_bracket; +} + +static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, + u64 total_samples, int depth, + int depth_mask, int left_margin) +{ + struct rb_node *node, *next; + struct callchain_node *child; + struct callchain_list *chain; + int new_depth_mask = depth_mask; + u64 remaining; + size_t ret = 0; + int i; + uint entries_printed = 0; + + remaining = total_samples; + + node = rb_first(root); + while (node) { + u64 new_total; + u64 cumul; + + child = rb_entry(node, struct callchain_node, rb_node); + cumul = callchain_cumul_hits(child); + remaining -= cumul; + + /* + * The depth mask manages the output of pipes that show + * the depth. We don't want to keep the pipes of the current + * level for the last child of this depth. + * Except if we have remaining filtered hits. They will + * supersede the last child + */ + next = rb_next(node); + if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining)) + new_depth_mask &= ~(1 << (depth - 1)); + + /* + * But we keep the older depth mask for the line separator + * to keep the level link until we reach the last child + */ + ret += ipchain__fprintf_graph_line(fp, depth, depth_mask, + left_margin); + i = 0; + list_for_each_entry(chain, &child->val, list) { + ret += ipchain__fprintf_graph(fp, chain, depth, + new_depth_mask, i++, + total_samples, + cumul, + left_margin); + } + + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = child->children_hit; + else + new_total = total_samples; + + ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total, + depth + 1, + new_depth_mask | (1 << depth), + left_margin); + node = next; + if (++entries_printed == callchain_param.print_limit) + break; + } + + if (callchain_param.mode == CHAIN_GRAPH_REL && + remaining && remaining != total_samples) { + + if (!rem_sq_bracket) + return ret; + + new_depth_mask &= ~(1 << (depth - 1)); + ret += ipchain__fprintf_graph(fp, &rem_hits, depth, + new_depth_mask, 0, total_samples, + remaining, left_margin); + } + + return ret; +} + +static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, + u64 total_samples, int left_margin) +{ + struct callchain_node *cnode; + struct callchain_list *chain; + u32 entries_printed = 0; + bool printed = false; + struct rb_node *node; + int i = 0; + int ret = 0; + + /* + * If have one single callchain root, don't bother printing + * its percentage (100 % in fractal mode and the same percentage + * than the hist in graph mode). This also avoid one level of column. + */ + node = rb_first(root); + if (node && !rb_next(node)) { + cnode = rb_entry(node, struct callchain_node, rb_node); + list_for_each_entry(chain, &cnode->val, list) { + /* + * If we sort by symbol, the first entry is the same than + * the symbol. No need to print it otherwise it appears as + * displayed twice. + */ + if (!i++ && sort__first_dimension == SORT_SYM) + continue; + if (!printed) { + ret += callchain__fprintf_left_margin(fp, left_margin); + ret += fprintf(fp, "|\n"); + ret += callchain__fprintf_left_margin(fp, left_margin); + ret += fprintf(fp, "---"); + left_margin += 3; + printed = true; + } else + ret += callchain__fprintf_left_margin(fp, left_margin); + + if (chain->ms.sym) + ret += fprintf(fp, " %s\n", chain->ms.sym->name); + else + ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); + + if (++entries_printed == callchain_param.print_limit) + break; + } + root = &cnode->rb_root; + } + + ret += __callchain__fprintf_graph(fp, root, total_samples, + 1, 1, left_margin); + ret += fprintf(fp, "\n"); + + return ret; +} + +static size_t __callchain__fprintf_flat(FILE *fp, + struct callchain_node *self, + u64 total_samples) +{ + struct callchain_list *chain; + size_t ret = 0; + + if (!self) + return 0; + + ret += __callchain__fprintf_flat(fp, self->parent, total_samples); + + + list_for_each_entry(chain, &self->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + if (chain->ms.sym) + ret += fprintf(fp, " %s\n", chain->ms.sym->name); + else + ret += fprintf(fp, " %p\n", + (void *)(long)chain->ip); + } + + return ret; +} + +static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self, + u64 total_samples) +{ + size_t ret = 0; + u32 entries_printed = 0; + struct rb_node *rb_node; + struct callchain_node *chain; + + rb_node = rb_first(self); + while (rb_node) { + double percent; + + chain = rb_entry(rb_node, struct callchain_node, rb_node); + percent = chain->hit * 100.0 / total_samples; + + ret = percent_color_fprintf(fp, " %6.2f%%\n", percent); + ret += __callchain__fprintf_flat(fp, chain, total_samples); + ret += fprintf(fp, "\n"); + if (++entries_printed == callchain_param.print_limit) + break; + + rb_node = rb_next(rb_node); + } + + return ret; +} + +static size_t hist_entry_callchain__fprintf(struct hist_entry *he, + u64 total_samples, int left_margin, + FILE *fp) +{ + switch (callchain_param.mode) { + case CHAIN_GRAPH_REL: + return callchain__fprintf_graph(fp, &he->sorted_chain, he->period, + left_margin); + break; + case CHAIN_GRAPH_ABS: + return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, + left_margin); + break; + case CHAIN_FLAT: + return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples); + break; + case CHAIN_NONE: + break; + default: + pr_err("Bad callchain mode\n"); + } + + return 0; +} + +static size_t hist_entry__callchain_fprintf(struct hist_entry *he, + struct hists *hists, + u64 total_period, FILE *fp) +{ + int left_margin = 0; + + if (sort__first_dimension == SORT_COMM) { + struct sort_entry *se = list_first_entry(&hist_entry__sort_list, + typeof(*se), list); + left_margin = hists__col_len(hists, se->se_width_idx); + left_margin -= thread__comm_len(he->thread); + } + + return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); +} + +static int hist_entry__fprintf(struct hist_entry *he, size_t size, + struct hists *hists, struct hists *pair_hists, + long displacement, u64 total_period, FILE *fp) +{ + char bf[512]; + int ret; + struct perf_hpp hpp = { + .buf = bf, + .size = size, + .total_period = total_period, + .displacement = displacement, + .ptr = pair_hists, + }; + bool color = !symbol_conf.field_sep; + + if (size == 0 || size > sizeof(bf)) + size = hpp.size = sizeof(bf); + + ret = hist_entry__period_snprintf(&hpp, he, color); + hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); + + ret = fprintf(fp, "%s\n", bf); + + if (symbol_conf.use_callchain) + ret += hist_entry__callchain_fprintf(he, hists, + total_period, fp); + + return ret; +} + +size_t hists__fprintf(struct hists *hists, struct hists *pair, + bool show_displacement, bool show_header, int max_rows, + int max_cols, FILE *fp) +{ + struct sort_entry *se; + struct rb_node *nd; + size_t ret = 0; + u64 total_period; + unsigned long position = 1; + long displacement = 0; + unsigned int width; + const char *sep = symbol_conf.field_sep; + const char *col_width = symbol_conf.col_width_list_str; + int idx, nr_rows = 0; + char bf[64]; + struct perf_hpp dummy_hpp = { + .buf = bf, + .size = sizeof(bf), + .ptr = pair, + }; + + init_rem_hits(); + + if (!show_header) + goto print_entries; + + fprintf(fp, "# "); + for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { + if (!perf_hpp__format[idx].cond) + continue; + + if (idx) + fprintf(fp, "%s", sep ?: " "); + + perf_hpp__format[idx].header(&dummy_hpp); + fprintf(fp, "%s", bf); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + if (sep) { + fprintf(fp, "%c%s", *sep, se->se_header); + continue; + } + width = strlen(se->se_header); + if (symbol_conf.col_width_list_str) { + if (col_width) { + hists__set_col_len(hists, se->se_width_idx, + atoi(col_width)); + col_width = strchr(col_width, ','); + if (col_width) + ++col_width; + } + } + if (!hists__new_col_len(hists, se->se_width_idx, width)) + width = hists__col_len(hists, se->se_width_idx); + fprintf(fp, " %*s", width, se->se_header); + } + + fprintf(fp, "\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; + + if (sep) + goto print_entries; + + fprintf(fp, "# "); + for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { + unsigned int i; + + if (!perf_hpp__format[idx].cond) + continue; + + if (idx) + fprintf(fp, "%s", sep ?: " "); + + width = perf_hpp__format[idx].width(&dummy_hpp); + for (i = 0; i < width; i++) + fprintf(fp, "."); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + unsigned int i; + + if (se->elide) + continue; + + fprintf(fp, " "); + width = hists__col_len(hists, se->se_width_idx); + if (width == 0) + width = strlen(se->se_header); + for (i = 0; i < width; i++) + fprintf(fp, "."); + } + + fprintf(fp, "\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; + + fprintf(fp, "#\n"); + if (max_rows && ++nr_rows >= max_rows) + goto out; + +print_entries: + total_period = hists->stats.total_period; + + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + if (h->filtered) + continue; + + if (show_displacement) { + if (h->pair != NULL) + displacement = ((long)h->pair->position - + (long)position); + else + displacement = 0; + ++position; + } + ret += hist_entry__fprintf(h, max_cols, hists, pair, displacement, + total_period, fp); + + if (max_rows && ++nr_rows >= max_rows) + goto out; + + if (h->ms.map == NULL && verbose > 1) { + __map_groups__fprintf_maps(&h->thread->mg, + MAP__FUNCTION, verbose, fp); + fprintf(fp, "%.10s end\n", graph_dotted_line); + } + } +out: + free(rem_sq_bracket); + + return ret; +} + +size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) +{ + int i; + size_t ret = 0; + + for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { + const char *name; + + if (hists->stats.nr_events[i] == 0) + continue; + + name = perf_event__name(i); + if (!strcmp(name, "UNKNOWN")) + continue; + + ret += fprintf(fp, "%16s events: %10d\n", name, + hists->stats.nr_events[i]); + } + + return ret; +} diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c new file mode 100644 index 000000000000..2884d2f41e33 --- /dev/null +++ b/tools/perf/ui/tui/helpline.c @@ -0,0 +1,57 @@ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <pthread.h> + +#include "../../util/debug.h" +#include "../helpline.h" +#include "../ui.h" +#include "../libslang.h" + +static void tui_helpline__pop(void) +{ +} + +static void tui_helpline__push(const char *msg) +{ + const size_t sz = sizeof(ui_helpline__current); + + SLsmg_gotorc(SLtt_Screen_Rows - 1, 0); + SLsmg_set_color(0); + SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols); + SLsmg_refresh(); + strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; +} + +struct ui_helpline tui_helpline_fns = { + .pop = tui_helpline__pop, + .push = tui_helpline__push, +}; + +void ui_helpline__init(void) +{ + helpline_fns = &tui_helpline_fns; + ui_helpline__puts(" "); +} + +char ui_helpline__last_msg[1024]; + +int ui_helpline__show_help(const char *format, va_list ap) +{ + int ret; + static int backlog; + + pthread_mutex_lock(&ui__lock); + ret = vscnprintf(ui_helpline__last_msg + backlog, + sizeof(ui_helpline__last_msg) - backlog, format, ap); + backlog += ret; + + if (ui_helpline__last_msg[backlog - 1] == '\n') { + ui_helpline__puts(ui_helpline__last_msg); + SLsmg_refresh(); + backlog = 0; + } + pthread_mutex_unlock(&ui__lock); + + return ret; +} diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index e813c1d17346..60debb81537a 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -11,12 +11,12 @@ #include "../libslang.h" #include "../keysyms.h" -pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; - static volatile int ui__need_resize; extern struct perf_error_ops perf_tui_eops; +extern void hist_browser__init_hpp(void); + void ui__refresh_dimensions(bool force) { if (force || ui__need_resize) { @@ -28,7 +28,7 @@ void ui__refresh_dimensions(bool force) } } -static void ui__sigwinch(int sig __used) +static void ui__sigwinch(int sig __maybe_unused) { ui__need_resize = 1; } @@ -88,7 +88,7 @@ int ui__getch(int delay_secs) return SLkp_getkey(); } -static void newt_suspend(void *d __used) +static void newt_suspend(void *d __maybe_unused) { newtSuspend(); raise(SIGTSTP); @@ -126,6 +126,8 @@ int ui__init(void) signal(SIGTERM, ui__signal); perf_error__register(&perf_tui_eops); + + hist_browser__init_hpp(); out: return err; } diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c index b8144e80bb1e..e6d134773d0a 100644 --- a/tools/perf/util/alias.c +++ b/tools/perf/util/alias.c @@ -3,7 +3,8 @@ static const char *alias_key; static char *alias_val; -static int alias_lookup_cb(const char *k, const char *v, void *cb __used) +static int alias_lookup_cb(const char *k, const char *v, + void *cb __maybe_unused) { if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { if (!v) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3a282c0057d2..f0a910371377 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,6 +17,7 @@ #include <pthread.h> const char *disassembler_style; +const char *objdump_path; static struct ins *ins__find(const char *name); static int disasm_line__parse(char *line, char **namep, char **rawp); @@ -312,8 +313,8 @@ static struct ins_ops dec_ops = { .scnprintf = dec__scnprintf, }; -static int nop__scnprintf(struct ins *ins __used, char *bf, size_t size, - struct ins_operands *ops __used) +static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size, + struct ins_operands *ops __maybe_unused) { return scnprintf(bf, size, "%-6.6s", "nop"); } @@ -415,7 +416,7 @@ static struct ins *ins__find(const char *name) return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp); } -int symbol__annotate_init(struct map *map __used, struct symbol *sym) +int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); pthread_mutex_init(¬es->lock, NULL); @@ -820,9 +821,10 @@ fallback: dso, dso->long_name, sym, sym->name); snprintf(command, sizeof(command), - "objdump %s%s --start-address=0x%016" PRIx64 + "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -d %s %s -C %s|grep -v %s|expand", + objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", map__rip_2objdump(map, sym->start), @@ -982,7 +984,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, int context) { struct dso *dso = map->dso; - const char *filename = dso->long_name, *d_filename; + char *filename; + const char *d_filename; struct annotation *notes = symbol__annotation(sym); struct disasm_line *pos, *queue = NULL; u64 start = map__rip_2objdump(map, sym->start); @@ -990,6 +993,10 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, int more = 0; u64 len; + filename = strdup(dso->long_name); + if (!filename) + return -ENOMEM; + if (full_paths) d_filename = filename; else @@ -1040,6 +1047,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, } } + free(filename); + return more; } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 78a5692dd718..9b5b21e7b032 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -7,6 +7,7 @@ #include "symbol.h" #include <linux/list.h> #include <linux/rbtree.h> +#include <pthread.h> struct ins; @@ -125,7 +126,7 @@ int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); -int symbol__annotate_init(struct map *map __used, struct symbol *sym); +int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym); int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, bool full_paths, int min_pcnt, int max_lines, int context); @@ -138,11 +139,12 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, int max_lines); #ifdef NO_NEWT_SUPPORT -static inline int symbol__tui_annotate(struct symbol *sym __used, - struct map *map __used, - int evidx __used, - void(*timer)(void *arg) __used, - void *arg __used, int delay_secs __used) +static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, + struct map *map __maybe_unused, + int evidx __maybe_unused, + void(*timer)(void *arg) __maybe_unused, + void *arg __maybe_unused, + int delay_secs __maybe_unused) { return 0; } @@ -152,5 +154,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, #endif extern const char *disassembler_style; +extern const char *objdump_path; #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index fd9a5944b627..8e3a740ddbd4 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -16,10 +16,10 @@ #include "session.h" #include "tool.h" -static int build_id__mark_dso_hit(struct perf_tool *tool __used, +static int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, - struct perf_evsel *evsel __used, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; @@ -41,9 +41,10 @@ static int build_id__mark_dso_hit(struct perf_tool *tool __used, return 0; } -static int perf_event__exit_del_thread(struct perf_tool *tool __used, +static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample + __maybe_unused, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, event->fork.tid); diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index cff18c617d13..ab1769426541 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -39,7 +39,7 @@ static inline void setup_browser(bool fallback_to_pager) if (fallback_to_pager) setup_pager(); } -static inline void exit_browser(bool wait_for_ok __used) {} +static inline void exit_browser(bool wait_for_ok __maybe_unused) {} #else void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); @@ -49,7 +49,7 @@ static inline int ui__init(void) { return -1; } -static inline void ui__exit(bool wait_for_ok __used) {} +static inline void ui__exit(bool wait_for_ok __maybe_unused) {} #else int ui__init(void); void ui__exit(bool wait_for_ok); @@ -60,7 +60,7 @@ static inline int perf_gtk__init(void) { return -1; } -static inline void perf_gtk__exit(bool wait_for_ok __used) {} +static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {} #else int perf_gtk__init(void); void perf_gtk__exit(bool wait_for_ok); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 3a6bff47614f..d3b3f5d82137 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -93,7 +93,7 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, */ static void sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root, - u64 min_hit, struct callchain_param *param __used) + u64 min_hit, struct callchain_param *param __maybe_unused) { __sort_chain_flat(rb_root, &root->node, min_hit); } @@ -115,7 +115,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node, static void sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root, - u64 min_hit, struct callchain_param *param __used) + u64 min_hit, struct callchain_param *param __maybe_unused) { __sort_chain_graph_abs(&chain_root->node, min_hit); rb_root->rb_node = chain_root->node.rb_root.rb_node; @@ -140,7 +140,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node, static void sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root, - u64 min_hit __used, struct callchain_param *param) + u64 min_hit __maybe_unused, struct callchain_param *param) { __sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0); rb_root->rb_node = chain_root->node.rb_root.rb_node; diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index dbe2f16b1a1a..96bbda1ddb83 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -138,8 +138,8 @@ void close_cgroup(struct cgroup_sel *cgrp) } } -int parse_cgroups(const struct option *opt __used, const char *str, - int unset __used) +int parse_cgroups(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; const char *p, *e, *eos = str + strlen(str); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 6faa3a18bfbd..3e0fdd369ccb 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -342,13 +342,15 @@ const char *perf_config_dirname(const char *name, const char *value) return value; } -static int perf_default_core_config(const char *var __used, const char *value __used) +static int perf_default_core_config(const char *var __maybe_unused, + const char *value __maybe_unused) { /* Add other config variables here. */ return 0; } -int perf_default_config(const char *var, const char *value, void *dummy __used) +int perf_default_config(const char *var, const char *value, + void *dummy __maybe_unused) { if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index adc72f09914d..2b32ffa9ebdb 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -38,24 +38,19 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) return cpus; } -static struct cpu_map *cpu_map__read_all_cpu_map(void) +struct cpu_map *cpu_map__read(FILE *file) { struct cpu_map *cpus = NULL; - FILE *onlnf; int nr_cpus = 0; int *tmp_cpus = NULL, *tmp; int max_entries = 0; int n, cpu, prev; char sep; - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (!onlnf) - return cpu_map__default_new(); - sep = 0; prev = -1; for (;;) { - n = fscanf(onlnf, "%u%c", &cpu, &sep); + n = fscanf(file, "%u%c", &cpu, &sep); if (n <= 0) break; if (prev >= 0) { @@ -95,6 +90,19 @@ static struct cpu_map *cpu_map__read_all_cpu_map(void) cpus = cpu_map__default_new(); out_free_tmp: free(tmp_cpus); + return cpus; +} + +static struct cpu_map *cpu_map__read_all_cpu_map(void) +{ + struct cpu_map *cpus = NULL; + FILE *onlnf; + + onlnf = fopen("/sys/devices/system/cpu/online", "r"); + if (!onlnf) + return cpu_map__default_new(); + + cpus = cpu_map__read(onlnf); fclose(onlnf); return cpus; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index c41518573c6a..2f68a3b8c285 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -2,6 +2,7 @@ #define __PERF_CPUMAP_H #include <stdio.h> +#include <stdbool.h> struct cpu_map { int nr; @@ -11,7 +12,17 @@ struct cpu_map { struct cpu_map *cpu_map__new(const char *cpu_list); struct cpu_map *cpu_map__dummy_new(void); void cpu_map__delete(struct cpu_map *map); - +struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); +static inline int cpu_map__nr(const struct cpu_map *map) +{ + return map ? map->nr : 1; +} + +static inline bool cpu_map__all(const struct cpu_map *map) +{ + return map ? map->map[0] == -1 : true; +} + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 4dfe0bb3c322..66eb3828ceb5 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -23,8 +23,10 @@ int eprintf(int level, const char *fmt, ...) if (verbose >= level) { va_start(args, fmt); - if (use_browser > 0) + if (use_browser == 1) ret = ui_helpline__show_help(fmt, args); + else if (use_browser == 2) + ret = perf_gtk__show_helpline(fmt, args); else ret = vfprintf(stderr, fmt, args); va_end(args); diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 015c91dbc096..bb2e7d1007ab 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -4,6 +4,7 @@ #include <stdbool.h> #include "event.h" +#include "../ui/helpline.h" extern int verbose; extern bool quiet, dump_trace; @@ -15,32 +16,26 @@ struct ui_progress; struct perf_error_ops; #if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) -static inline int ui_helpline__show_help(const char *format __used, va_list ap __used) -{ - return 0; -} - -static inline void ui_progress__update(u64 curr __used, u64 total __used, - const char *title __used) {} +static inline void ui_progress__update(u64 curr __maybe_unused, + u64 total __maybe_unused, + const char *title __maybe_unused) {} #define ui__error(format, arg...) ui__warning(format, ##arg) static inline int -perf_error__register(struct perf_error_ops *eops __used) +perf_error__register(struct perf_error_ops *eops __maybe_unused) { return 0; } static inline int -perf_error__unregister(struct perf_error_ops *eops __used) +perf_error__unregister(struct perf_error_ops *eops __maybe_unused) { return 0; } #else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ -extern char ui_helpline__last_msg[]; -int ui_helpline__show_help(const char *format, va_list ap); #include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); #include "../ui/util.h" diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/util/dso-test-data.c index 541cdc72c7df..c6caedeb1d6b 100644 --- a/tools/perf/util/dso-test-data.c +++ b/tools/perf/util/dso-test-data.c @@ -23,7 +23,7 @@ static char *test_file(int size) int fd, i; unsigned char *buf; - fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC); + fd = mkstemp(templ); buf = malloc(size); if (!buf) { diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index ee51e9b4dc09..3e5f5430a28a 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -804,6 +804,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len) tmp = "union "; else if (tag == DW_TAG_structure_type) tmp = "struct "; + else if (tag == DW_TAG_enumeration_type) + tmp = "enum "; /* Write a base name */ ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type)); return (ret >= len) ? -E2BIG : ret; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2a6f33cd888c..6715b1938725 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -112,7 +112,7 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, event->comm.header.type = PERF_RECORD_COMM; size = strlen(event->comm.comm) + 1; - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); memset(event->comm.comm + size, 0, machine->id_hdr_size); event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + @@ -120,7 +120,9 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, if (!full) { event->comm.tid = pid; - process(tool, event, &synth_sample, machine); + if (process(tool, event, &synth_sample, machine) != 0) + return -1; + goto out; } @@ -143,7 +145,7 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, sizeof(event->comm.comm)); size = strlen(event->comm.comm) + 1; - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); memset(event->comm.comm + size, 0, machine->id_hdr_size); event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + @@ -151,7 +153,10 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, event->comm.tid = pid; - process(tool, event, &synth_sample, machine); + if (process(tool, event, &synth_sample, machine) != 0) { + tgid = -1; + break; + } } closedir(tasks); @@ -167,6 +172,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, { char filename[PATH_MAX]; FILE *fp; + int rc = 0; snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); @@ -222,7 +228,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, size = strlen(execname); execname[size - 1] = '\0'; /* Remove \n */ memcpy(event->mmap.filename, execname, size); - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); event->mmap.len -= event->mmap.start; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); @@ -231,18 +237,22 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, event->mmap.pid = tgid; event->mmap.tid = pid; - process(tool, event, &synth_sample, machine); + if (process(tool, event, &synth_sample, machine) != 0) { + rc = -1; + break; + } } } fclose(fp); - return 0; + return rc; } int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine) { + int rc = 0; struct rb_node *nd; struct map_groups *kmaps = &machine->kmaps; union perf_event *event = zalloc((sizeof(event->mmap) + @@ -272,7 +282,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, if (pos->dso->kernel) continue; - size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); @@ -284,11 +294,14 @@ int perf_event__synthesize_modules(struct perf_tool *tool, memcpy(event->mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); - process(tool, event, &synth_sample, machine); + if (process(tool, event, &synth_sample, machine) != 0) { + rc = -1; + break; + } } free(event); - return 0; + return rc; } static int __event__synthesize_thread(union perf_event *comm_event, @@ -392,12 +405,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (*end) /* only interested in proper numerical dirents */ continue; - __event__synthesize_thread(comm_event, mmap_event, pid, 1, - process, tool, machine); + if (__event__synthesize_thread(comm_event, mmap_event, pid, 1, + process, tool, machine) != 0) { + err = -1; + goto out_closedir; + } } - closedir(proc); err = 0; +out_closedir: + closedir(proc); out_free_mmap: free(mmap_event); out_free_comm: @@ -412,7 +429,7 @@ struct process_symbol_args { }; static int find_symbol_cb(void *arg, const char *name, char type, - u64 start, u64 end __used) + u64 start) { struct process_symbol_args *args = arg; @@ -477,7 +494,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, map = machine->vmlinux_maps[MAP__FUNCTION]; size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), "%s%s", mmap_name, symbol_name) + 1; - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); @@ -497,9 +514,9 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid); } -int perf_event__process_comm(struct perf_tool *tool __used, +int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample __maybe_unused, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, event->comm.tid); @@ -515,10 +532,10 @@ int perf_event__process_comm(struct perf_tool *tool __used, return 0; } -int perf_event__process_lost(struct perf_tool *tool __used, +int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, - struct machine *machine __used) + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", event->lost.id, event->lost.lost); @@ -538,7 +555,8 @@ static void perf_event__set_kernel_mmap_len(union perf_event *event, maps[MAP__FUNCTION]->end = ~0ULL; } -static int perf_event__process_kernel_mmap(struct perf_tool *tool __used, +static int perf_event__process_kernel_mmap(struct perf_tool *tool + __maybe_unused, union perf_event *event, struct machine *machine) { @@ -640,7 +658,7 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample __maybe_unused, struct machine *machine) { struct thread *thread; @@ -684,9 +702,9 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) event->fork.ppid, event->fork.ptid); } -int perf_event__process_task(struct perf_tool *tool __used, +int perf_event__process_task(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __used, + struct perf_sample *sample __maybe_unused, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, event->fork.tid); @@ -886,8 +904,9 @@ int perf_event__preprocess_sample(const union perf_event *event, al->sym = map__find_symbol(al->map, al->addr, filter); } - if (symbol_conf.sym_list && al->sym && - !strlist__has_entry(symbol_conf.sym_list, al->sym->name)) + if (symbol_conf.sym_list && + (!al->sym || !strlist__has_entry(symbol_conf.sym_list, + al->sym->name))) goto out_filtered; return 0; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index d84870b06426..21b99e741a87 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -69,6 +69,16 @@ struct sample_event { u64 array[]; }; +struct regs_dump { + u64 *regs; +}; + +struct stack_dump { + u16 offset; + u64 size; + char *data; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -82,6 +92,8 @@ struct perf_sample { void *raw_data; struct ip_callchain *callchain; struct branch_stack *branch_stack; + struct regs_dump user_regs; + struct stack_dump user_stack; }; #define BUILD_ID_SIZE 20 @@ -89,7 +101,7 @@ struct perf_sample { struct build_id_event { struct perf_event_header header; pid_t pid; - u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[]; }; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9b38681add9e..ae89686102f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -57,7 +57,7 @@ void perf_evlist__config_attrs(struct perf_evlist *evlist, if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - first = list_entry(evlist->entries.next, struct perf_evsel, node); + first = perf_evlist__first(evlist); list_for_each_entry(evsel, &evlist->entries, node) { perf_evsel__config(evsel, opts, first); @@ -108,6 +108,25 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist, evlist->nr_entries += nr_entries; } +void __perf_evlist__set_leader(struct list_head *list) +{ + struct perf_evsel *evsel, *leader; + + leader = list_entry(list->next, struct perf_evsel, node); + leader->leader = NULL; + + list_for_each_entry(evsel, list, node) { + if (evsel != leader) + evsel->leader = leader; + } +} + +void perf_evlist__set_leader(struct perf_evlist *evlist) +{ + if (evlist->nr_entries) + __perf_evlist__set_leader(&evlist->entries); +} + int perf_evlist__add_default(struct perf_evlist *evlist) { struct perf_event_attr attr = { @@ -285,7 +304,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) int cpu, thread; struct perf_evsel *pos; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) { list_for_each_entry(pos, &evlist->entries, node) { for (thread = 0; thread < evlist->threads->nr; thread++) ioctl(FD(pos, cpu, thread), @@ -296,7 +315,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries; + int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries; evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); return evlist->pollfd != NULL ? 0 : -ENOMEM; } @@ -357,7 +376,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) int hash; if (evlist->nr_entries == 1) - return list_entry(evlist->entries.next, struct perf_evsel, node); + return perf_evlist__first(evlist); hash = hash_64(id, PERF_EVLIST__HLIST_BITS); head = &evlist->heads[hash]; @@ -367,7 +386,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return sid->evsel; if (!perf_evlist__sample_id_all(evlist)) - return list_entry(evlist->entries.next, struct perf_evsel, node); + return perf_evlist__first(evlist); return NULL; } @@ -456,8 +475,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist) static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { - evlist->nr_mmaps = evlist->cpus->nr; - if (evlist->cpus->map[0] == -1) + evlist->nr_mmaps = cpu_map__nr(evlist->cpus); + if (cpu_map__all(evlist->cpus)) evlist->nr_mmaps = evlist->threads->nr; evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; @@ -603,11 +622,11 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, list_for_each_entry(evsel, &evlist->entries, node) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0) return -ENOMEM; } - if (evlist->cpus->map[0] == -1) + if (cpu_map__all(cpus)) return perf_evlist__mmap_per_thread(evlist, prot, mask); return perf_evlist__mmap_per_cpu(evlist, prot, mask); @@ -647,39 +666,44 @@ void perf_evlist__delete_maps(struct perf_evlist *evlist) evlist->threads = NULL; } -int perf_evlist__set_filters(struct perf_evlist *evlist) +int perf_evlist__apply_filters(struct perf_evlist *evlist) { - const struct thread_map *threads = evlist->threads; - const struct cpu_map *cpus = evlist->cpus; struct perf_evsel *evsel; - char *filter; - int thread; - int cpu; - int err; - int fd; + int err = 0; + const int ncpus = cpu_map__nr(evlist->cpus), + nthreads = evlist->threads->nr; list_for_each_entry(evsel, &evlist->entries, node) { - filter = evsel->filter; - if (!filter) + if (evsel->filter == NULL) continue; - for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { - fd = FD(evsel, cpu, thread); - err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter); - if (err) - return err; - } - } + + err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter); + if (err) + break; } - return 0; + return err; } -bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist) +int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) { - struct perf_evsel *pos, *first; + struct perf_evsel *evsel; + int err = 0; + const int ncpus = cpu_map__nr(evlist->cpus), + nthreads = evlist->threads->nr; + + list_for_each_entry(evsel, &evlist->entries, node) { + err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter); + if (err) + break; + } + + return err; +} - pos = first = list_entry(evlist->entries.next, struct perf_evsel, node); +bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; list_for_each_entry_continue(pos, &evlist->entries, node) { if (first->attr.sample_type != pos->attr.sample_type) @@ -689,23 +713,19 @@ bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist) return true; } -u64 perf_evlist__sample_type(const struct perf_evlist *evlist) +u64 perf_evlist__sample_type(struct perf_evlist *evlist) { - struct perf_evsel *first; - - first = list_entry(evlist->entries.next, struct perf_evsel, node); + struct perf_evsel *first = perf_evlist__first(evlist); return first->attr.sample_type; } -u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist) +u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) { - struct perf_evsel *first; + struct perf_evsel *first = perf_evlist__first(evlist); struct perf_sample *data; u64 sample_type; u16 size = 0; - first = list_entry(evlist->entries.next, struct perf_evsel, node); - if (!first->attr.sample_id_all) goto out; @@ -729,11 +749,9 @@ out: return size; } -bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist) +bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist) { - struct perf_evsel *pos, *first; - - pos = first = list_entry(evlist->entries.next, struct perf_evsel, node); + struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; list_for_each_entry_continue(pos, &evlist->entries, node) { if (first->attr.sample_id_all != pos->attr.sample_id_all) @@ -743,11 +761,9 @@ bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist) return true; } -bool perf_evlist__sample_id_all(const struct perf_evlist *evlist) +bool perf_evlist__sample_id_all(struct perf_evlist *evlist) { - struct perf_evsel *first; - - first = list_entry(evlist->entries.next, struct perf_evsel, node); + struct perf_evsel *first = perf_evlist__first(evlist); return first->attr.sample_id_all; } @@ -757,21 +773,13 @@ void perf_evlist__set_selected(struct perf_evlist *evlist, evlist->selected = evsel; } -int perf_evlist__open(struct perf_evlist *evlist, bool group) +int perf_evlist__open(struct perf_evlist *evlist) { - struct perf_evsel *evsel, *first; + struct perf_evsel *evsel; int err, ncpus, nthreads; - first = list_entry(evlist->entries.next, struct perf_evsel, node); - list_for_each_entry(evsel, &evlist->entries, node) { - struct xyarray *group_fd = NULL; - - if (group && evsel != first) - group_fd = first->fd; - - err = perf_evsel__open(evsel, evlist->cpus, evlist->threads, - group, group_fd); + err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); if (err < 0) goto out_err; } @@ -883,8 +891,21 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) } int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, - struct perf_sample *sample, bool swapped) + struct perf_sample *sample) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + return perf_evsel__parse_sample(evsel, event, sample); +} + +size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) { - struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node); - return perf_evsel__parse_sample(e, event, sample, swapped); + struct perf_evsel *evsel; + size_t printed = 0; + + list_for_each_entry(evsel, &evlist->entries, node) { + printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "", + perf_evsel__name(evsel)); + } + + return printed + fprintf(fp, "\n");; } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 528c1acd9298..3f1fb66be022 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -5,6 +5,7 @@ #include <stdio.h> #include "../perf.h" #include "event.h" +#include "evsel.h" #include "util.h" #include <unistd.h> @@ -41,8 +42,6 @@ struct perf_evsel_str_handler { void *handler; }; -struct perf_evsel; - struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, @@ -73,6 +72,8 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, #define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) +int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); + struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); @@ -85,7 +86,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); -int perf_evlist__open(struct perf_evlist *evlist, bool group); +int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__config_attrs(struct perf_evlist *evlist, struct perf_record_opts *opts); @@ -116,20 +117,34 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, int perf_evlist__create_maps(struct perf_evlist *evlist, struct perf_target *target); void perf_evlist__delete_maps(struct perf_evlist *evlist); -int perf_evlist__set_filters(struct perf_evlist *evlist); +int perf_evlist__apply_filters(struct perf_evlist *evlist); + +void __perf_evlist__set_leader(struct list_head *list); +void perf_evlist__set_leader(struct perf_evlist *evlist); -u64 perf_evlist__sample_type(const struct perf_evlist *evlist); -bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist); -u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist); +u64 perf_evlist__sample_type(struct perf_evlist *evlist); +bool perf_evlist__sample_id_all(struct perf_evlist *evlist); +u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, - struct perf_sample *sample, bool swapped); + struct perf_sample *sample); -bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist); -bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist); +bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); +bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, int nr_entries); +static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.next, struct perf_evsel, node); +} + +static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.prev, struct perf_evsel, node); +} + +size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 2eaae140def2..ffdd94e9c9c3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -8,7 +8,10 @@ */ #include <byteswap.h> +#include <linux/bitops.h> #include "asm/bug.h" +#include "debugfs.h" +#include "event-parse.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -16,9 +19,10 @@ #include "thread_map.h" #include "target.h" #include "../../../include/linux/hw_breakpoint.h" +#include "../../include/linux/perf_event.h" +#include "perf_regs.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0)) static int __perf_evsel__sample_size(u64 sample_type) { @@ -66,7 +70,80 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) return evsel; } -static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = { +struct event_format *event_format__new(const char *sys, const char *name) +{ + int fd, n; + char *filename; + void *bf = NULL, *nbf; + size_t size = 0, alloc_size = 0; + struct event_format *format = NULL; + + if (asprintf(&filename, "%s/%s/%s/format", tracing_events_path, sys, name) < 0) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out_free_filename; + + do { + if (size == alloc_size) { + alloc_size += BUFSIZ; + nbf = realloc(bf, alloc_size); + if (nbf == NULL) + goto out_free_bf; + bf = nbf; + } + + n = read(fd, bf + size, BUFSIZ); + if (n < 0) + goto out_free_bf; + size += n; + } while (n > 0); + + pevent_parse_format(&format, bf, size, sys); + +out_free_bf: + free(bf); + close(fd); +out_free_filename: + free(filename); +out: + return format; +} + +struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx) +{ + struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + + if (evsel != NULL) { + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), + }; + + if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) + goto out_free; + + evsel->tp_format = event_format__new(sys, name); + if (evsel->tp_format == NULL) + goto out_free; + + event_attr_init(&attr); + attr.config = evsel->tp_format->id; + attr.sample_period = 1; + perf_evsel__init(evsel, &attr, idx); + } + + return evsel; + +out_free: + free(evsel->name); + free(evsel); + return NULL; +} + +const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = { "cycles", "instructions", "cache-references", @@ -129,12 +206,12 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); } -static const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { +const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { "cpu-clock", "task-clock", "page-faults", "context-switches", - "CPU-migrations", + "cpu-migrations", "minor-faults", "major-faults", "alignment-faults", @@ -317,7 +394,8 @@ const char *perf_evsel__name(struct perf_evsel *evsel) break; default: - scnprintf(bf, sizeof(bf), "%s", "unknown attr type"); + scnprintf(bf, sizeof(bf), "unknown attr type: %d", + evsel->attr.type); break; } @@ -367,9 +445,18 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, attr->mmap_data = track; } - if (opts->call_graph) + if (opts->call_graph) { attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + if (opts->call_graph == CALLCHAIN_DWARF) { + attr->sample_type |= PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_STACK_USER; + attr->sample_regs_user = PERF_REGS_MASK; + attr->sample_stack_user = opts->stack_dump_size; + attr->exclude_callchain_user = 1; + } + } + if (perf_target__has_cpu(&opts->target)) attr->sample_type |= PERF_SAMPLE_CPU; @@ -421,6 +508,24 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) return evsel->fd != NULL ? 0 : -ENOMEM; } +int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter) +{ + int cpu, thread; + + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + int fd = FD(evsel, cpu, thread), + err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter); + + if (err) + return err; + } + } + + return 0; +} + int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); @@ -481,6 +586,9 @@ void perf_evsel__delete(struct perf_evsel *evsel) { perf_evsel__exit(evsel); close_cgroup(evsel->cgrp); + free(evsel->group_name); + if (evsel->tp_format) + pevent_free_format(evsel->tp_format); free(evsel->name); free(evsel); } @@ -556,9 +664,28 @@ int __perf_evsel__read(struct perf_evsel *evsel, return 0; } +static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) +{ + struct perf_evsel *leader = evsel->leader; + int fd; + + if (!leader) + return -1; + + /* + * Leader must be already processed/open, + * if not it's a bug. + */ + BUG_ON(!leader->fd); + + fd = FD(leader, cpu, thread); + BUG_ON(fd == -1); + + return fd; +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group, - struct xyarray *group_fds) + struct thread_map *threads) { int cpu, thread; unsigned long flags = 0; @@ -574,13 +701,15 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } for (cpu = 0; cpu < cpus->nr; cpu++) { - int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1; for (thread = 0; thread < threads->nr; thread++) { + int group_fd; if (!evsel->cgrp) pid = threads->map[thread]; + group_fd = get_group_fd(evsel, cpu, thread); + FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], @@ -589,9 +718,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, err = -errno; goto out_close; } - - if (group && group_fd == -1) - group_fd = FD(evsel, cpu, thread); } } @@ -635,8 +761,7 @@ static struct { }; int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group, - struct xyarray *group_fd) + struct thread_map *threads) { if (cpus == NULL) { /* Work around old compiler warnings about strict aliasing */ @@ -646,30 +771,28 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, if (threads == NULL) threads = &empty_thread_map.map; - return __perf_evsel__open(evsel, cpus, threads, group, group_fd); + return __perf_evsel__open(evsel, cpus, threads); } int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus, bool group, - struct xyarray *group_fd) + struct cpu_map *cpus) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, - group_fd); + return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); } int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads, bool group, - struct xyarray *group_fd) + struct thread_map *threads) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, - group_fd); + return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); } -static int perf_event__parse_id_sample(const union perf_event *event, u64 type, - struct perf_sample *sample, - bool swapped) +static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, + const union perf_event *event, + struct perf_sample *sample) { + u64 type = evsel->attr.sample_type; const u64 *array = event->sample.array; + bool swapped = evsel->needs_swap; union u64_swap u; array += ((event->header.size - @@ -730,9 +853,11 @@ static bool sample_overlap(const union perf_event *event, } int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, - struct perf_sample *data, bool swapped) + struct perf_sample *data) { u64 type = evsel->attr.sample_type; + u64 regs_user = evsel->attr.sample_regs_user; + bool swapped = evsel->needs_swap; const u64 *array; /* @@ -749,7 +874,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (event->header.type != PERF_RECORD_SAMPLE) { if (!evsel->attr.sample_id_all) return 0; - return perf_event__parse_id_sample(event, type, data, swapped); + return perf_evsel__parse_id_sample(evsel, event, data); } array = event->sample.array; @@ -869,6 +994,32 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, sz /= sizeof(u64); array += sz; } + + if (type & PERF_SAMPLE_REGS_USER) { + /* First u64 tells us if we have any regs in sample. */ + u64 avail = *array++; + + if (avail) { + data->user_regs.regs = (u64 *)array; + array += hweight_long(regs_user); + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + u64 size = *array++; + + data->user_stack.offset = ((char *)(array - 1) + - (char *) event); + + if (!size) { + data->user_stack.size = 0; + } else { + data->user_stack.data = (char *)array; + array += size / sizeof(*array); + data->user_stack.size = *array; + } + } + return 0; } @@ -947,3 +1098,72 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, return 0; } + +struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) +{ + return pevent_find_field(evsel->tp_format, name); +} + +void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name) +{ + struct format_field *field = perf_evsel__field(evsel, name); + int offset; + + if (!field) + return NULL; + + offset = field->offset; + + if (field->flags & FIELD_IS_DYNAMIC) { + offset = *(int *)(sample->raw_data + field->offset); + offset &= 0xffff; + } + + return sample->raw_data + offset; +} + +u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name) +{ + struct format_field *field = perf_evsel__field(evsel, name); + void *ptr; + u64 value; + + if (!field) + return 0; + + ptr = sample->raw_data + field->offset; + + switch (field->size) { + case 1: + return *(u8 *)ptr; + case 2: + value = *(u16 *)ptr; + break; + case 4: + value = *(u32 *)ptr; + break; + case 8: + value = *(u64 *)ptr; + break; + default: + return 0; + } + + if (!evsel->needs_swap) + return value; + + switch (field->size) { + case 2: + return bswap_16(value); + case 4: + return bswap_32(value); + case 8: + return bswap_64(value); + default: + return 0; + } + + return 0; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index b559929983bb..3ead0d59c03d 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -53,9 +53,10 @@ struct perf_evsel { u64 *id; struct perf_counts *counts; int idx; - int ids; + u32 ids; struct hists hists; char *name; + struct event_format *tp_format; union { void *priv; off_t id_offset; @@ -65,8 +66,14 @@ struct perf_evsel { void *func; void *data; } handler; + struct cpu_map *cpus; unsigned int sample_size; bool supported; + bool needs_swap; + /* parse modifier helper */ + int exclude_GH; + struct perf_evsel *leader; + char *group_name; }; struct cpu_map; @@ -75,6 +82,10 @@ struct perf_evlist; struct perf_record_opts; struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx); +struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx); + +struct event_format *event_format__new(const char *sys, const char *name); + void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx); void perf_evsel__exit(struct perf_evsel *evsel); @@ -92,8 +103,10 @@ extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] [PERF_EVSEL__MAX_ALIASES]; extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] [PERF_EVSEL__MAX_ALIASES]; -const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] - [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX]; +extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *perf_evsel__name(struct perf_evsel *evsel); @@ -105,21 +118,46 @@ void perf_evsel__free_fd(struct perf_evsel *evsel); void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter); + int perf_evsel__open_per_cpu(struct perf_evsel *evsel, - struct cpu_map *cpus, bool group, - struct xyarray *group_fds); + struct cpu_map *cpus); int perf_evsel__open_per_thread(struct perf_evsel *evsel, - struct thread_map *threads, bool group, - struct xyarray *group_fds); + struct thread_map *threads); int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads, bool group, - struct xyarray *group_fds); + struct thread_map *threads); void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads); +struct perf_sample; + +void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name); +u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name); + +static inline char *perf_evsel__strval(struct perf_evsel *evsel, + struct perf_sample *sample, + const char *name) +{ + return perf_evsel__rawptr(evsel, sample, name); +} + +struct format_field; + +struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); + #define perf_evsel__match(evsel, t, c) \ (evsel->attr.type == PERF_TYPE_##t && \ evsel->attr.config == PERF_COUNT_##c) +static inline bool perf_evsel__match2(struct perf_evsel *e1, + struct perf_evsel *e2) +{ + return (e1->attr.type == e2->attr.type) && + (e1->attr.config == e2->attr.config); +} + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); @@ -181,5 +219,10 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel, void hists__init(struct hists *hists); int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, - struct perf_sample *sample, bool swapped); + struct perf_sample *sample); + +static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) +{ + return list_entry(evsel->node.next, struct perf_evsel, node); +} #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index f06f6fd148f8..389590c1ad21 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -21,4 +21,19 @@ do p }' "Documentation/perf-$cmd.txt" done + +echo "#ifndef NO_LIBELF_SUPPORT" +sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "#endif /* NO_LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 74ea3c2f8138..7daad237dea5 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -20,11 +20,14 @@ #include "symbol.h" #include "debug.h" #include "cpumap.h" +#include "pmu.h" +#include "vdso.h" +#include "strbuf.h" static bool no_buildid_cache = false; -static int event_count; -static struct perf_trace_event_type *events; +static int trace_event_count; +static struct perf_trace_event_type *trace_events; static u32 header_argc; static const char **header_argv; @@ -36,24 +39,24 @@ int perf_header__push_event(u64 id, const char *name) if (strlen(name) > MAX_EVENT_NAME) pr_warning("Event %s will be truncated\n", name); - nevents = realloc(events, (event_count + 1) * sizeof(*events)); + nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events)); if (nevents == NULL) return -ENOMEM; - events = nevents; + trace_events = nevents; - memset(&events[event_count], 0, sizeof(struct perf_trace_event_type)); - events[event_count].event_id = id; - strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1); - event_count++; + memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type)); + trace_events[trace_event_count].event_id = id; + strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1); + trace_event_count++; return 0; } char *perf_header__find_event(u64 id) { int i; - for (i = 0 ; i < event_count; i++) { - if (events[i].event_id == id) - return events[i].name; + for (i = 0 ; i < trace_event_count; i++) { + if (trace_events[i].event_id == id) + return trace_events[i].name; } return NULL; } @@ -128,7 +131,7 @@ static int do_write_string(int fd, const char *str) int ret; olen = strlen(str) + 1; - len = ALIGN(olen, NAME_ALIGN); + len = PERF_ALIGN(olen, NAME_ALIGN); /* write len, incl. \0 */ ret = do_write(fd, &len, sizeof(len)); @@ -206,6 +209,29 @@ perf_header__set_cmdline(int argc, const char **argv) continue; \ else +static int write_buildid(char *name, size_t name_len, u8 *build_id, + pid_t pid, u16 misc, int fd) +{ + int err; + struct build_id_event b; + size_t len; + + len = name_len + 1; + len = PERF_ALIGN(len, NAME_ALIGN); + + memset(&b, 0, sizeof(b)); + memcpy(&b.build_id, build_id, BUILD_ID_SIZE); + b.pid = pid; + b.header.misc = misc; + b.header.size = sizeof(b) + len; + + err = do_write(fd, &b, sizeof(b)); + if (err < 0) + return err; + + return write_padded(fd, name, name_len + 1, len); +} + static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, u16 misc, int fd) { @@ -213,24 +239,23 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, dsos__for_each_with_build_id(pos, head) { int err; - struct build_id_event b; - size_t len; + char *name; + size_t name_len; if (!pos->hit) continue; - len = pos->long_name_len + 1; - len = ALIGN(len, NAME_ALIGN); - memset(&b, 0, sizeof(b)); - memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id)); - b.pid = pid; - b.header.misc = misc; - b.header.size = sizeof(b) + len; - err = do_write(fd, &b, sizeof(b)); - if (err < 0) - return err; - err = write_padded(fd, pos->long_name, - pos->long_name_len + 1, len); - if (err < 0) + + if (is_vdso_map(pos->short_name)) { + name = (char *) VDSO__MAP_NAME; + name_len = sizeof(VDSO__MAP_NAME) + 1; + } else { + name = pos->long_name; + name_len = pos->long_name_len + 1; + } + + err = write_buildid(name, name_len, pos->build_id, + pid, misc, fd); + if (err) return err; } @@ -276,19 +301,20 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd) } int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms) + const char *name, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; char *realname, *filename = zalloc(size), *linkname = zalloc(size), *targetname; int len, err = -1; + bool slash = is_kallsyms || is_vdso; if (is_kallsyms) { if (symbol_conf.kptr_restrict) { pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); return 0; } - realname = (char *)name; + realname = (char *) name; } else realname = realpath(name, NULL); @@ -296,7 +322,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, goto out_free; len = scnprintf(filename, size, "%s%s%s", - debugdir, is_kallsyms ? "/" : "", realname); + debugdir, slash ? "/" : "", + is_vdso ? VDSO__MAP_NAME : realname); if (mkdir_p(filename, 0755)) goto out_free; @@ -332,13 +359,14 @@ out_free: static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, const char *name, const char *debugdir, - bool is_kallsyms) + bool is_kallsyms, bool is_vdso) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms); + return build_id_cache__add_s(sbuild_id, debugdir, name, + is_kallsyms, is_vdso); } int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) @@ -382,9 +410,11 @@ out_free: static int dso__cache_build_id(struct dso *dso, const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; + bool is_vdso = is_vdso_map(dso->short_name); return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, is_kallsyms); + dso->long_name, debugdir, + is_kallsyms, is_vdso); } static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) @@ -446,7 +476,7 @@ static bool perf_session__read_build_ids(struct perf_session *session, bool with return ret; } -static int write_tracing_data(int fd, struct perf_header *h __used, +static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist) { return read_tracing_data(fd, &evlist->entries); @@ -454,7 +484,7 @@ static int write_tracing_data(int fd, struct perf_header *h __used, static int write_build_id(int fd, struct perf_header *h, - struct perf_evlist *evlist __used) + struct perf_evlist *evlist __maybe_unused) { struct perf_session *session; int err; @@ -475,8 +505,8 @@ static int write_build_id(int fd, struct perf_header *h, return 0; } -static int write_hostname(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_hostname(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -488,8 +518,8 @@ static int write_hostname(int fd, struct perf_header *h __used, return do_write_string(fd, uts.nodename); } -static int write_osrelease(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_osrelease(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -501,8 +531,8 @@ static int write_osrelease(int fd, struct perf_header *h __used, return do_write_string(fd, uts.release); } -static int write_arch(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_arch(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { struct utsname uts; int ret; @@ -514,14 +544,14 @@ static int write_arch(int fd, struct perf_header *h __used, return do_write_string(fd, uts.machine); } -static int write_version(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_version(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return do_write_string(fd, perf_version_string); } -static int write_cpudesc(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { #ifndef CPUINFO_PROC #define CPUINFO_PROC NULL @@ -579,8 +609,8 @@ done: return ret; } -static int write_nrcpus(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { long nr; u32 nrc, nra; @@ -605,15 +635,14 @@ static int write_nrcpus(int fd, struct perf_header *h __used, return do_write(fd, &nra, sizeof(nra)); } -static int write_event_desc(int fd, struct perf_header *h __used, +static int write_event_desc(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist) { - struct perf_evsel *attr; - u32 nre = 0, nri, sz; + struct perf_evsel *evsel; + u32 nre, nri, sz; int ret; - list_for_each_entry(attr, &evlist->entries, node) - nre++; + nre = evlist->nr_entries; /* * write number of events @@ -625,14 +654,14 @@ static int write_event_desc(int fd, struct perf_header *h __used, /* * size of perf_event_attr struct */ - sz = (u32)sizeof(attr->attr); + sz = (u32)sizeof(evsel->attr); ret = do_write(fd, &sz, sizeof(sz)); if (ret < 0) return ret; - list_for_each_entry(attr, &evlist->entries, node) { + list_for_each_entry(evsel, &evlist->entries, node) { - ret = do_write(fd, &attr->attr, sz); + ret = do_write(fd, &evsel->attr, sz); if (ret < 0) return ret; /* @@ -642,7 +671,7 @@ static int write_event_desc(int fd, struct perf_header *h __used, * copy into an nri to be independent of the * type of ids, */ - nri = attr->ids; + nri = evsel->ids; ret = do_write(fd, &nri, sizeof(nri)); if (ret < 0) return ret; @@ -650,21 +679,21 @@ static int write_event_desc(int fd, struct perf_header *h __used, /* * write event string as passed on cmdline */ - ret = do_write_string(fd, perf_evsel__name(attr)); + ret = do_write_string(fd, perf_evsel__name(evsel)); if (ret < 0) return ret; /* * write unique ids for this event */ - ret = do_write(fd, attr->id, attr->ids * sizeof(u64)); + ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); if (ret < 0) return ret; } return 0; } -static int write_cmdline(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_cmdline(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { char buf[MAXPATHLEN]; char proc[32]; @@ -832,8 +861,8 @@ static struct cpu_topo *build_cpu_topology(void) return tp; } -static int write_cpu_topology(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { struct cpu_topo *tp; u32 i; @@ -868,8 +897,8 @@ done: -static int write_total_mem(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_total_mem(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -954,8 +983,8 @@ done: return ret; } -static int write_numa_topology(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; size_t len = 0; @@ -1004,16 +1033,56 @@ done: } /* + * File format: + * + * struct pmu_mappings { + * u32 pmu_num; + * struct pmu_map { + * u32 type; + * char name[]; + * }[pmu_num]; + * }; + */ + +static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + struct perf_pmu *pmu = NULL; + off_t offset = lseek(fd, 0, SEEK_CUR); + __u32 pmu_num = 0; + + /* write real pmu_num later */ + do_write(fd, &pmu_num, sizeof(pmu_num)); + + while ((pmu = perf_pmu__scan(pmu))) { + if (!pmu->name) + continue; + pmu_num++; + do_write(fd, &pmu->type, sizeof(pmu->type)); + do_write_string(fd, pmu->name); + } + + if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { + /* discard all */ + lseek(fd, offset, SEEK_SET); + return -1; + } + + return 0; +} + +/* * default get_cpuid(): nothing gets recorded * actual implementation must be in arch/$(ARCH)/util/header.c */ -int __attribute__((weak)) get_cpuid(char *buffer __used, size_t sz __used) +int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused, + size_t sz __maybe_unused) { return -1; } -static int write_cpuid(int fd, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_cpuid(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { char buffer[64]; int ret; @@ -1027,133 +1096,113 @@ write_it: return do_write_string(fd, buffer); } -static int write_branch_stack(int fd __used, struct perf_header *h __used, - struct perf_evlist *evlist __used) +static int write_branch_stack(int fd __maybe_unused, + struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return 0; } -static void print_hostname(struct perf_header *ph, int fd, FILE *fp) +static void print_hostname(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# hostname : %s\n", str); - free(str); + fprintf(fp, "# hostname : %s\n", ph->env.hostname); } -static void print_osrelease(struct perf_header *ph, int fd, FILE *fp) +static void print_osrelease(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# os release : %s\n", str); - free(str); + fprintf(fp, "# os release : %s\n", ph->env.os_release); } -static void print_arch(struct perf_header *ph, int fd, FILE *fp) +static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# arch : %s\n", str); - free(str); + fprintf(fp, "# arch : %s\n", ph->env.arch); } -static void print_cpudesc(struct perf_header *ph, int fd, FILE *fp) +static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# cpudesc : %s\n", str); - free(str); + fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc); } -static void print_nrcpus(struct perf_header *ph, int fd, FILE *fp) +static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - ssize_t ret; - u32 nr; - - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - nr = -1; /* interpreted as error */ - - if (ph->needs_swap) - nr = bswap_32(nr); - - fprintf(fp, "# nrcpus online : %u\n", nr); - - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - nr = -1; /* interpreted as error */ - - if (ph->needs_swap) - nr = bswap_32(nr); - - fprintf(fp, "# nrcpus avail : %u\n", nr); + fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online); + fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail); } -static void print_version(struct perf_header *ph, int fd, FILE *fp) +static void print_version(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# perf version : %s\n", str); - free(str); + fprintf(fp, "# perf version : %s\n", ph->env.version); } -static void print_cmdline(struct perf_header *ph, int fd, FILE *fp) +static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - ssize_t ret; + int nr, i; char *str; - u32 nr, i; - - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - return; - if (ph->needs_swap) - nr = bswap_32(nr); + nr = ph->env.nr_cmdline; + str = ph->env.cmdline; fprintf(fp, "# cmdline : "); for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); fprintf(fp, "%s ", str); - free(str); + str += strlen(str) + 1; } fputc('\n', fp); } -static void print_cpu_topology(struct perf_header *ph, int fd, FILE *fp) +static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - ssize_t ret; - u32 nr, i; + int nr, i; char *str; - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - return; - - if (ph->needs_swap) - nr = bswap_32(nr); + nr = ph->env.nr_sibling_cores; + str = ph->env.sibling_cores; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); fprintf(fp, "# sibling cores : %s\n", str); - free(str); + str += strlen(str) + 1; } - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - return; - - if (ph->needs_swap) - nr = bswap_32(nr); + nr = ph->env.nr_sibling_threads; + str = ph->env.sibling_threads; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); fprintf(fp, "# sibling threads : %s\n", str); - free(str); + str += strlen(str) + 1; } } -static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +static void free_event_desc(struct perf_evsel *events) +{ + struct perf_evsel *evsel; + + if (!events) + return; + + for (evsel = events; evsel->attr.size; evsel++) { + if (evsel->name) + free(evsel->name); + if (evsel->id) + free(evsel->id); + } + + free(events); +} + +static struct perf_evsel * +read_event_desc(struct perf_header *ph, int fd) { - struct perf_event_attr attr; - uint64_t id; + struct perf_evsel *evsel, *events = NULL; + u64 *id; void *buf = NULL; - char *str; u32 nre, sz, nr, i, j; ssize_t ret; size_t msz; @@ -1173,18 +1222,22 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) if (ph->needs_swap) sz = bswap_32(sz); - memset(&attr, 0, sizeof(attr)); - /* buffer to hold on file attr struct */ buf = malloc(sz); if (!buf) goto error; - msz = sizeof(attr); + /* the last event terminates with evsel->attr.size == 0: */ + events = calloc(nre + 1, sizeof(*events)); + if (!events) + goto error; + + msz = sizeof(evsel->attr); if (sz < msz) msz = sz; - for (i = 0 ; i < nre; i++) { + for (i = 0, evsel = events; i < nre; evsel++, i++) { + evsel->idx = i; /* * must read entire on-file attr struct to @@ -1197,146 +1250,188 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) if (ph->needs_swap) perf_event__attr_swap(buf); - memcpy(&attr, buf, msz); + memcpy(&evsel->attr, buf, msz); ret = read(fd, &nr, sizeof(nr)); if (ret != (ssize_t)sizeof(nr)) goto error; - if (ph->needs_swap) + if (ph->needs_swap) { nr = bswap_32(nr); + evsel->needs_swap = true; + } - str = do_read_string(fd, ph); - fprintf(fp, "# event : name = %s, ", str); - free(str); + evsel->name = do_read_string(fd, ph); + + if (!nr) + continue; + + id = calloc(nr, sizeof(*id)); + if (!id) + goto error; + evsel->ids = nr; + evsel->id = id; + + for (j = 0 ; j < nr; j++) { + ret = read(fd, id, sizeof(*id)); + if (ret != (ssize_t)sizeof(*id)) + goto error; + if (ph->needs_swap) + *id = bswap_64(*id); + id++; + } + } +out: + if (buf) + free(buf); + return events; +error: + if (events) + free_event_desc(events); + events = NULL; + goto out; +} + +static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +{ + struct perf_evsel *evsel, *events = read_event_desc(ph, fd); + u32 j; + u64 *id; + + if (!events) { + fprintf(fp, "# event desc: not available or unable to read\n"); + return; + } + + for (evsel = events; evsel->attr.size; evsel++) { + fprintf(fp, "# event : name = %s, ", evsel->name); fprintf(fp, "type = %d, config = 0x%"PRIx64 ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64, - attr.type, - (u64)attr.config, - (u64)attr.config1, - (u64)attr.config2); + evsel->attr.type, + (u64)evsel->attr.config, + (u64)evsel->attr.config1, + (u64)evsel->attr.config2); fprintf(fp, ", excl_usr = %d, excl_kern = %d", - attr.exclude_user, - attr.exclude_kernel); + evsel->attr.exclude_user, + evsel->attr.exclude_kernel); fprintf(fp, ", excl_host = %d, excl_guest = %d", - attr.exclude_host, - attr.exclude_guest); + evsel->attr.exclude_host, + evsel->attr.exclude_guest); - fprintf(fp, ", precise_ip = %d", attr.precise_ip); + fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip); - if (nr) + if (evsel->ids) { fprintf(fp, ", id = {"); - - for (j = 0 ; j < nr; j++) { - ret = read(fd, &id, sizeof(id)); - if (ret != (ssize_t)sizeof(id)) - goto error; - - if (ph->needs_swap) - id = bswap_64(id); - - if (j) - fputc(',', fp); - - fprintf(fp, " %"PRIu64, id); - } - if (nr && j == nr) + for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { + if (j) + fputc(',', fp); + fprintf(fp, " %"PRIu64, *id); + } fprintf(fp, " }"); + } + fputc('\n', fp); } - free(buf); - return; -error: - fprintf(fp, "# event desc: not available or unable to read\n"); + + free_event_desc(events); } -static void print_total_mem(struct perf_header *h __used, int fd, FILE *fp) +static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - uint64_t mem; - ssize_t ret; - - ret = read(fd, &mem, sizeof(mem)); - if (ret != sizeof(mem)) - goto error; - - if (h->needs_swap) - mem = bswap_64(mem); - - fprintf(fp, "# total memory : %"PRIu64" kB\n", mem); - return; -error: - fprintf(fp, "# total memory : unknown\n"); + fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem); } -static void print_numa_topology(struct perf_header *h __used, int fd, FILE *fp) +static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) { - ssize_t ret; u32 nr, c, i; - char *str; + char *str, *tmp; uint64_t mem_total, mem_free; /* nr nodes */ - ret = read(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) - goto error; - - if (h->needs_swap) - nr = bswap_32(nr); + nr = ph->env.nr_numa_nodes; + str = ph->env.numa_nodes; for (i = 0; i < nr; i++) { - /* node number */ - ret = read(fd, &c, sizeof(c)); - if (ret != (ssize_t)sizeof(c)) + c = strtoul(str, &tmp, 0); + if (*tmp != ':') goto error; - if (h->needs_swap) - c = bswap_32(c); - - ret = read(fd, &mem_total, sizeof(u64)); - if (ret != sizeof(u64)) + str = tmp + 1; + mem_total = strtoull(str, &tmp, 0); + if (*tmp != ':') goto error; - ret = read(fd, &mem_free, sizeof(u64)); - if (ret != sizeof(u64)) + str = tmp + 1; + mem_free = strtoull(str, &tmp, 0); + if (*tmp != ':') goto error; - if (h->needs_swap) { - mem_total = bswap_64(mem_total); - mem_free = bswap_64(mem_free); - } - fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," " free = %"PRIu64" kB\n", - c, - mem_total, - mem_free); + c, mem_total, mem_free); - str = do_read_string(fd, h); + str = tmp + 1; fprintf(fp, "# node%u cpu list : %s\n", c, str); - free(str); } return; error: fprintf(fp, "# numa topology : not available\n"); } -static void print_cpuid(struct perf_header *ph, int fd, FILE *fp) +static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { - char *str = do_read_string(fd, ph); - fprintf(fp, "# cpuid : %s\n", str); - free(str); + fprintf(fp, "# cpuid : %s\n", ph->env.cpuid); } -static void print_branch_stack(struct perf_header *ph __used, int fd __used, - FILE *fp) +static void print_branch_stack(struct perf_header *ph __maybe_unused, + int fd __maybe_unused, FILE *fp) { fprintf(fp, "# contains samples with branch stack\n"); } +static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + const char *delimiter = "# pmu mappings: "; + char *str, *tmp; + u32 pmu_num; + u32 type; + + pmu_num = ph->env.nr_pmu_mappings; + if (!pmu_num) { + fprintf(fp, "# pmu mappings: not available\n"); + return; + } + + str = ph->env.pmu_mappings; + + while (pmu_num) { + type = strtoul(str, &tmp, 0); + if (*tmp != ':') + goto error; + + str = tmp + 1; + fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type); + + delimiter = ", "; + str += strlen(str) + 1; + pmu_num--; + } + + fprintf(fp, "\n"); + + if (!pmu_num) + return; +error: + fprintf(fp, "# pmu mappings: unable to read\n"); +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -1398,7 +1493,7 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, struct perf_session *session = container_of(header, struct perf_session, header); struct { struct perf_event_header header; - u8 build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))]; + u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))]; char filename[0]; } old_bev; struct build_id_event bev; @@ -1487,28 +1582,375 @@ out: return err; } -static int process_tracing_data(struct perf_file_section *section __unused, - struct perf_header *ph __unused, - int feat __unused, int fd, void *data) +static int process_tracing_data(struct perf_file_section *section __maybe_unused, + struct perf_header *ph __maybe_unused, + int fd, void *data) { trace_report(fd, data, false); return 0; } static int process_build_id(struct perf_file_section *section, - struct perf_header *ph, - int feat __unused, int fd, void *data __used) + struct perf_header *ph, int fd, + void *data __maybe_unused) { if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) pr_debug("Failed to read buildids, continuing...\n"); return 0; } +static int process_hostname(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.hostname = do_read_string(fd, ph); + return ph->env.hostname ? 0 : -ENOMEM; +} + +static int process_osrelease(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.os_release = do_read_string(fd, ph); + return ph->env.os_release ? 0 : -ENOMEM; +} + +static int process_version(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.version = do_read_string(fd, ph); + return ph->env.version ? 0 : -ENOMEM; +} + +static int process_arch(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.arch = do_read_string(fd, ph); + return ph->env.arch ? 0 : -ENOMEM; +} + +static int process_nrcpus(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret; + u32 nr; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cpus_online = nr; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cpus_avail = nr; + return 0; +} + +static int process_cpudesc(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.cpu_desc = do_read_string(fd, ph); + return ph->env.cpu_desc ? 0 : -ENOMEM; +} + +static int process_cpuid(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + ph->env.cpuid = do_read_string(fd, ph); + return ph->env.cpuid ? 0 : -ENOMEM; +} + +static int process_total_mem(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + uint64_t mem; + size_t ret; + + ret = read(fd, &mem, sizeof(mem)); + if (ret != sizeof(mem)) + return -1; + + if (ph->needs_swap) + mem = bswap_64(mem); + + ph->env.total_mem = mem; + return 0; +} + +static struct perf_evsel * +perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->idx == idx) + return evsel; + } + + return NULL; +} + +static void +perf_evlist__set_event_name(struct perf_evlist *evlist, + struct perf_evsel *event) +{ + struct perf_evsel *evsel; + + if (!event->name) + return; + + evsel = perf_evlist__find_by_index(evlist, event->idx); + if (!evsel) + return; + + if (evsel->name) + return; + + evsel->name = strdup(event->name); +} + +static int +process_event_desc(struct perf_file_section *section __maybe_unused, + struct perf_header *header, int fd, + void *data __maybe_unused) +{ + struct perf_session *session; + struct perf_evsel *evsel, *events = read_event_desc(header, fd); + + if (!events) + return 0; + + session = container_of(header, struct perf_session, header); + for (evsel = events; evsel->attr.size; evsel++) + perf_evlist__set_event_name(session->evlist, evsel); + + free_event_desc(events); + + return 0; +} + +static int process_cmdline(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret; + char *str; + u32 nr, i; + struct strbuf sb; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_cmdline = nr; + strbuf_init(&sb, 128); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.cmdline = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + +static int process_cpu_topology(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret; + u32 nr, i; + char *str; + struct strbuf sb; + + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_sibling_cores = nr; + strbuf_init(&sb, 128); + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.sibling_cores = strbuf_detach(&sb, NULL); + + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + return -1; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_sibling_threads = nr; + + for (i = 0; i < nr; i++) { + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.sibling_threads = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + +static int process_numa_topology(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret; + u32 nr, node, i; + char *str; + uint64_t mem_total, mem_free; + struct strbuf sb; + + /* nr nodes */ + ret = read(fd, &nr, sizeof(nr)); + if (ret != sizeof(nr)) + goto error; + + if (ph->needs_swap) + nr = bswap_32(nr); + + ph->env.nr_numa_nodes = nr; + strbuf_init(&sb, 256); + + for (i = 0; i < nr; i++) { + /* node number */ + ret = read(fd, &node, sizeof(node)); + if (ret != sizeof(node)) + goto error; + + ret = read(fd, &mem_total, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + ret = read(fd, &mem_free, sizeof(u64)); + if (ret != sizeof(u64)) + goto error; + + if (ph->needs_swap) { + node = bswap_32(node); + mem_total = bswap_64(mem_total); + mem_free = bswap_64(mem_free); + } + + strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", + node, mem_total, mem_free); + + str = do_read_string(fd, ph); + if (!str) + goto error; + + /* include a NULL character at the end */ + strbuf_add(&sb, str, strlen(str) + 1); + free(str); + } + ph->env.numa_nodes = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + +static int process_pmu_mappings(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret; + char *name; + u32 pmu_num; + u32 type; + struct strbuf sb; + + ret = read(fd, &pmu_num, sizeof(pmu_num)); + if (ret != sizeof(pmu_num)) + return -1; + + if (ph->needs_swap) + pmu_num = bswap_32(pmu_num); + + if (!pmu_num) { + pr_debug("pmu mappings not available\n"); + return 0; + } + + ph->env.nr_pmu_mappings = pmu_num; + strbuf_init(&sb, 128); + + while (pmu_num) { + if (read(fd, &type, sizeof(type)) != sizeof(type)) + goto error; + if (ph->needs_swap) + type = bswap_32(type); + + name = do_read_string(fd, ph); + if (!name) + goto error; + + strbuf_addf(&sb, "%u:%s", type, name); + /* include a NULL character at the end */ + strbuf_add(&sb, "", 1); + + free(name); + pmu_num--; + } + ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + return 0; + +error: + strbuf_release(&sb); + return -1; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); int (*process)(struct perf_file_section *section, - struct perf_header *h, int feat, int fd, void *data); + struct perf_header *h, int fd, void *data); const char *name; bool full_only; }; @@ -1520,7 +1962,7 @@ struct feature_ops { .process = process_##func } #define FEAT_OPF(n, func) \ [n] = { .name = #n, .write = write_##func, .print = print_##func, \ - .full_only = true } + .process = process_##func, .full_only = true } /* feature_ops not implemented: */ #define print_tracing_data NULL @@ -1529,19 +1971,20 @@ struct feature_ops { static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPP(HEADER_TRACING_DATA, tracing_data), FEAT_OPP(HEADER_BUILD_ID, build_id), - FEAT_OPA(HEADER_HOSTNAME, hostname), - FEAT_OPA(HEADER_OSRELEASE, osrelease), - FEAT_OPA(HEADER_VERSION, version), - FEAT_OPA(HEADER_ARCH, arch), - FEAT_OPA(HEADER_NRCPUS, nrcpus), - FEAT_OPA(HEADER_CPUDESC, cpudesc), - FEAT_OPA(HEADER_CPUID, cpuid), - FEAT_OPA(HEADER_TOTAL_MEM, total_mem), - FEAT_OPA(HEADER_EVENT_DESC, event_desc), - FEAT_OPA(HEADER_CMDLINE, cmdline), + FEAT_OPP(HEADER_HOSTNAME, hostname), + FEAT_OPP(HEADER_OSRELEASE, osrelease), + FEAT_OPP(HEADER_VERSION, version), + FEAT_OPP(HEADER_ARCH, arch), + FEAT_OPP(HEADER_NRCPUS, nrcpus), + FEAT_OPP(HEADER_CPUDESC, cpudesc), + FEAT_OPP(HEADER_CPUID, cpuid), + FEAT_OPP(HEADER_TOTAL_MEM, total_mem), + FEAT_OPP(HEADER_EVENT_DESC, event_desc), + FEAT_OPP(HEADER_CMDLINE, cmdline), FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), + FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), }; struct header_print_data { @@ -1683,17 +2126,17 @@ int perf_session__write_header(struct perf_session *session, struct perf_file_header f_header; struct perf_file_attr f_attr; struct perf_header *header = &session->header; - struct perf_evsel *attr, *pair = NULL; + struct perf_evsel *evsel, *pair = NULL; int err; lseek(fd, sizeof(f_header), SEEK_SET); if (session->evlist != evlist) - pair = list_entry(session->evlist->entries.next, struct perf_evsel, node); + pair = perf_evlist__first(session->evlist); - list_for_each_entry(attr, &evlist->entries, node) { - attr->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(fd, attr->id, attr->ids * sizeof(u64)); + list_for_each_entry(evsel, &evlist->entries, node) { + evsel->id_offset = lseek(fd, 0, SEEK_CUR); + err = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); if (err < 0) { out_err_write: pr_debug("failed to write perf header\n"); @@ -1703,19 +2146,19 @@ out_err_write: err = do_write(fd, pair->id, pair->ids * sizeof(u64)); if (err < 0) goto out_err_write; - attr->ids += pair->ids; - pair = list_entry(pair->node.next, struct perf_evsel, node); + evsel->ids += pair->ids; + pair = perf_evsel__next(pair); } } header->attr_offset = lseek(fd, 0, SEEK_CUR); - list_for_each_entry(attr, &evlist->entries, node) { + list_for_each_entry(evsel, &evlist->entries, node) { f_attr = (struct perf_file_attr){ - .attr = attr->attr, + .attr = evsel->attr, .ids = { - .offset = attr->id_offset, - .size = attr->ids * sizeof(u64), + .offset = evsel->id_offset, + .size = evsel->ids * sizeof(u64), } }; err = do_write(fd, &f_attr, sizeof(f_attr)); @@ -1726,9 +2169,9 @@ out_err_write: } header->event_offset = lseek(fd, 0, SEEK_CUR); - header->event_size = event_count * sizeof(struct perf_trace_event_type); - if (events) { - err = do_write(fd, events, header->event_size); + header->event_size = trace_event_count * sizeof(struct perf_trace_event_type); + if (trace_events) { + err = do_write(fd, trace_events, header->event_size); if (err < 0) { pr_debug("failed to write perf header events\n"); return err; @@ -1829,6 +2272,8 @@ out_free: static const int attr_file_abi_sizes[] = { [0] = PERF_ATTR_SIZE_VER0, [1] = PERF_ATTR_SIZE_VER1, + [2] = PERF_ATTR_SIZE_VER2, + [3] = PERF_ATTR_SIZE_VER3, 0, }; @@ -2019,7 +2464,7 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, feat, fd, data); + return feat_ops[feat].process(section, ph, fd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, @@ -2108,32 +2553,39 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel, - struct pevent *pevent) +static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, + struct pevent *pevent) { - struct event_format *event = pevent_find_event(pevent, - evsel->attr.config); + struct event_format *event; char bf[128]; + /* already prepared */ + if (evsel->tp_format) + return 0; + + event = pevent_find_event(pevent, evsel->attr.config); if (event == NULL) return -1; - snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); - evsel->name = strdup(bf); - if (event->name == NULL) - return -1; + if (!evsel->name) { + snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); + evsel->name = strdup(bf); + if (evsel->name == NULL) + return -1; + } + evsel->tp_format = event; return 0; } -static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist, - struct pevent *pevent) +static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, + struct pevent *pevent) { struct perf_evsel *pos; list_for_each_entry(pos, &evlist->entries, node) { if (pos->attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__set_tracepoint_name(pos, pevent)) + perf_evsel__prepare_tracepoint_event(pos, pevent)) return -1; } @@ -2176,6 +2628,8 @@ int perf_session__read_header(struct perf_session *session, int fd) if (evsel == NULL) goto out_delete_evlist; + + evsel->needs_swap = header->needs_swap; /* * Do it before so that if perf_evsel__alloc_id fails, this * entry gets purged too at perf_evlist__delete(). @@ -2207,13 +2661,13 @@ int perf_session__read_header(struct perf_session *session, int fd) if (f_header.event_types.size) { lseek(fd, f_header.event_types.offset, SEEK_SET); - events = malloc(f_header.event_types.size); - if (events == NULL) + trace_events = malloc(f_header.event_types.size); + if (trace_events == NULL) return -ENOMEM; - if (perf_header__getbuffer64(header, fd, events, + if (perf_header__getbuffer64(header, fd, trace_events, f_header.event_types.size)) goto out_errno; - event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); + trace_event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } perf_header__process_sections(header, fd, &session->pevent, @@ -2221,7 +2675,8 @@ int perf_session__read_header(struct perf_session *session, int fd) lseek(fd, header->data_offset, SEEK_SET); - if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent)) + if (perf_evlist__prepare_tracepoint_events(session->evlist, + session->pevent)) goto out_delete_evlist; header->frozen = 1; @@ -2236,7 +2691,7 @@ out_delete_evlist: } int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u16 ids, u64 *id, + struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process) { union perf_event *ev; @@ -2244,7 +2699,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, int err; size = sizeof(struct perf_event_attr); - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); size += sizeof(struct perf_event_header); size += ids * sizeof(u64); @@ -2257,9 +2712,12 @@ int perf_event__synthesize_attr(struct perf_tool *tool, memcpy(ev->attr.id, id, ids * sizeof(u64)); ev->attr.header.type = PERF_RECORD_HEADER_ATTR; - ev->attr.header.size = size; + ev->attr.header.size = (u16)size; - err = process(tool, ev, NULL, NULL); + if (ev->attr.header.size == size) + err = process(tool, ev, NULL, NULL); + else + err = -E2BIG; free(ev); @@ -2270,12 +2728,12 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process) { - struct perf_evsel *attr; + struct perf_evsel *evsel; int err = 0; - list_for_each_entry(attr, &session->evlist->entries, node) { - err = perf_event__synthesize_attr(tool, &attr->attr, attr->ids, - attr->id, process); + list_for_each_entry(evsel, &session->evlist->entries, node) { + err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, + evsel->id, process); if (err) { pr_debug("failed to create perf header attribute\n"); return err; @@ -2288,7 +2746,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist) { - unsigned int i, ids, n_ids; + u32 i, ids, n_ids; struct perf_evsel *evsel; struct perf_evlist *evlist = *pevlist; @@ -2339,7 +2797,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool, ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; size = strlen(ev.event_type.event_type.name); - size = ALIGN(size, sizeof(u64)); + size = PERF_ALIGN(size, sizeof(u64)); ev.event_type.header.size = sizeof(ev.event_type) - (sizeof(ev.event_type.event_type.name) - size); @@ -2355,8 +2813,8 @@ int perf_event__synthesize_event_types(struct perf_tool *tool, struct perf_trace_event_type *type; int i, err = 0; - for (i = 0; i < event_count; i++) { - type = &events[i]; + for (i = 0; i < trace_event_count; i++) { + type = &trace_events[i]; err = perf_event__synthesize_event_type(tool, type->event_id, type->name, process, @@ -2370,7 +2828,7 @@ int perf_event__synthesize_event_types(struct perf_tool *tool, return err; } -int perf_event__process_event_type(struct perf_tool *tool __unused, +int perf_event__process_event_type(struct perf_tool *tool __maybe_unused, union perf_event *event) { if (perf_header__push_event(event->event_type.event_type.event_id, @@ -2387,7 +2845,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, union perf_event ev; struct tracing_data *tdata; ssize_t size = 0, aligned_size = 0, padding; - int err __used = 0; + int err __maybe_unused = 0; /* * We are going to store the size of the data followed @@ -2408,7 +2866,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; size = tdata->size; - aligned_size = ALIGN(size, sizeof(u64)); + aligned_size = PERF_ALIGN(size, sizeof(u64)); padding = aligned_size - size; ev.tracing_data.header.size = sizeof(ev.tracing_data); ev.tracing_data.size = aligned_size; @@ -2439,7 +2897,7 @@ int perf_event__process_tracing_data(union perf_event *event, size_read = trace_report(session->fd, &session->pevent, session->repipe); - padding = ALIGN(size_read, sizeof(u64)) - size_read; + padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; if (read(session->fd, buf, padding) < 0) die("reading input file"); @@ -2452,6 +2910,9 @@ int perf_event__process_tracing_data(union perf_event *event, if (size_read + padding != size) die("tracing data size mismatch"); + perf_evlist__prepare_tracepoint_events(session->evlist, + session->pevent); + return size_read + padding; } @@ -2470,7 +2931,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, memset(&ev, 0, sizeof(ev)); len = pos->long_name_len + 1; - len = ALIGN(len, NAME_ALIGN); + len = PERF_ALIGN(len, NAME_ALIGN); memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc; @@ -2483,7 +2944,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, return err; } -int perf_event__process_build_id(struct perf_tool *tool __used, +int perf_event__process_build_id(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 2d42b3e1826f..99bdd3abce59 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -28,6 +28,7 @@ enum { HEADER_CPU_TOPOLOGY, HEADER_NUMA_TOPOLOGY, HEADER_BRANCH_STACK, + HEADER_PMU_MAPPINGS, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -57,6 +58,29 @@ struct perf_header; int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd); +struct perf_session_env { + char *hostname; + char *os_release; + char *version; + char *arch; + int nr_cpus_online; + int nr_cpus_avail; + char *cpu_desc; + char *cpuid; + unsigned long long total_mem; + + int nr_cmdline; + char *cmdline; + int nr_sibling_cores; + char *sibling_cores; + int nr_sibling_threads; + char *sibling_threads; + int nr_numa_nodes; + char *numa_nodes; + int nr_pmu_mappings; + char *pmu_mappings; +}; + struct perf_header { int frozen; bool needs_swap; @@ -66,6 +90,7 @@ struct perf_header { u64 event_offset; u64 event_size; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); + struct perf_session_env env; }; struct perf_evlist; @@ -95,11 +120,11 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms); + const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); int perf_event__synthesize_attr(struct perf_tool *tool, - struct perf_event_attr *attr, u16 ids, u64 *id, + struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c index 6f2975a00358..8b1f6e891b8a 100644 --- a/tools/perf/util/help.c +++ b/tools/perf/util/help.c @@ -3,6 +3,7 @@ #include "exec_cmd.h" #include "levenshtein.h" #include "help.h" +#include <termios.h> void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) { @@ -331,7 +332,8 @@ const char *help_unknown_cmd(const char *cmd) exit(1); } -int cmd_version(int argc __used, const char **argv __used, const char *prefix __used) +int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, + const char *prefix __maybe_unused) { printf("perf version %s\n", perf_version_string); return 0; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f247ef2789a4..236bc9d98ff2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -45,7 +45,7 @@ bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len) return false; } -static void hists__reset_col_len(struct hists *hists) +void hists__reset_col_len(struct hists *hists) { enum hist_column col; @@ -63,7 +63,7 @@ static void hists__set_unres_dso_col_len(struct hists *hists, int dso) hists__set_col_len(hists, dso, unresolved_col_width); } -static void hists__calc_col_len(struct hists *hists, struct hist_entry *h) +void hists__calc_col_len(struct hists *hists, struct hist_entry *h) { const unsigned int unresolved_col_width = BITS_PER_LONG / 4; u16 len; @@ -114,6 +114,22 @@ static void hists__calc_col_len(struct hists *hists, struct hist_entry *h) } } +void hists__output_recalc_col_len(struct hists *hists, int max_rows) +{ + struct rb_node *next = rb_first(&hists->entries); + struct hist_entry *n; + int row = 0; + + hists__reset_col_len(hists); + + while (next && row++ < max_rows) { + n = rb_entry(next, struct hist_entry, rb_node); + if (!n->filtered) + hists__calc_col_len(hists, n); + next = rb_next(&n->rb_node); + } +} + static void hist_entry__add_cpumode_period(struct hist_entry *he, unsigned int cpumode, u64 period) { @@ -378,7 +394,7 @@ void hist_entry__free(struct hist_entry *he) * collapse the histogram */ -static bool hists__collapse_insert_entry(struct hists *hists __used, +static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, struct rb_root *root, struct hist_entry *he) { @@ -394,8 +410,13 @@ static bool hists__collapse_insert_entry(struct hists *hists __used, cmp = hist_entry__collapse(iter, he); if (!cmp) { - iter->period += he->period; - iter->nr_events += he->nr_events; + iter->period += he->period; + iter->period_sys += he->period_sys; + iter->period_us += he->period_us; + iter->period_guest_sys += he->period_guest_sys; + iter->period_guest_us += he->period_guest_us; + iter->nr_events += he->nr_events; + if (symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); callchain_merge(&callchain_cursor, @@ -547,674 +568,6 @@ void hists__output_resort_threaded(struct hists *hists) return __hists__output_resort(hists, true); } -static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) -{ - int i; - int ret = fprintf(fp, " "); - - for (i = 0; i < left_margin; i++) - ret += fprintf(fp, " "); - - return ret; -} - -static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, - int left_margin) -{ - int i; - size_t ret = callchain__fprintf_left_margin(fp, left_margin); - - for (i = 0; i < depth; i++) - if (depth_mask & (1 << i)) - ret += fprintf(fp, "| "); - else - ret += fprintf(fp, " "); - - ret += fprintf(fp, "\n"); - - return ret; -} - -static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, - int depth, int depth_mask, int period, - u64 total_samples, u64 hits, - int left_margin) -{ - int i; - size_t ret = 0; - - ret += callchain__fprintf_left_margin(fp, left_margin); - for (i = 0; i < depth; i++) { - if (depth_mask & (1 << i)) - ret += fprintf(fp, "|"); - else - ret += fprintf(fp, " "); - if (!period && i == depth - 1) { - double percent; - - percent = hits * 100.0 / total_samples; - ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent); - } else - ret += fprintf(fp, "%s", " "); - } - if (chain->ms.sym) - ret += fprintf(fp, "%s\n", chain->ms.sym->name); - else - ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip); - - return ret; -} - -static struct symbol *rem_sq_bracket; -static struct callchain_list rem_hits; - -static void init_rem_hits(void) -{ - rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6); - if (!rem_sq_bracket) { - fprintf(stderr, "Not enough memory to display remaining hits\n"); - return; - } - - strcpy(rem_sq_bracket->name, "[...]"); - rem_hits.ms.sym = rem_sq_bracket; -} - -static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, - u64 total_samples, int depth, - int depth_mask, int left_margin) -{ - struct rb_node *node, *next; - struct callchain_node *child; - struct callchain_list *chain; - int new_depth_mask = depth_mask; - u64 remaining; - size_t ret = 0; - int i; - uint entries_printed = 0; - - remaining = total_samples; - - node = rb_first(root); - while (node) { - u64 new_total; - u64 cumul; - - child = rb_entry(node, struct callchain_node, rb_node); - cumul = callchain_cumul_hits(child); - remaining -= cumul; - - /* - * The depth mask manages the output of pipes that show - * the depth. We don't want to keep the pipes of the current - * level for the last child of this depth. - * Except if we have remaining filtered hits. They will - * supersede the last child - */ - next = rb_next(node); - if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining)) - new_depth_mask &= ~(1 << (depth - 1)); - - /* - * But we keep the older depth mask for the line separator - * to keep the level link until we reach the last child - */ - ret += ipchain__fprintf_graph_line(fp, depth, depth_mask, - left_margin); - i = 0; - list_for_each_entry(chain, &child->val, list) { - ret += ipchain__fprintf_graph(fp, chain, depth, - new_depth_mask, i++, - total_samples, - cumul, - left_margin); - } - - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = child->children_hit; - else - new_total = total_samples; - - ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total, - depth + 1, - new_depth_mask | (1 << depth), - left_margin); - node = next; - if (++entries_printed == callchain_param.print_limit) - break; - } - - if (callchain_param.mode == CHAIN_GRAPH_REL && - remaining && remaining != total_samples) { - - if (!rem_sq_bracket) - return ret; - - new_depth_mask &= ~(1 << (depth - 1)); - ret += ipchain__fprintf_graph(fp, &rem_hits, depth, - new_depth_mask, 0, total_samples, - remaining, left_margin); - } - - return ret; -} - -static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, - u64 total_samples, int left_margin) -{ - struct callchain_node *cnode; - struct callchain_list *chain; - u32 entries_printed = 0; - bool printed = false; - struct rb_node *node; - int i = 0; - int ret = 0; - - /* - * If have one single callchain root, don't bother printing - * its percentage (100 % in fractal mode and the same percentage - * than the hist in graph mode). This also avoid one level of column. - */ - node = rb_first(root); - if (node && !rb_next(node)) { - cnode = rb_entry(node, struct callchain_node, rb_node); - list_for_each_entry(chain, &cnode->val, list) { - /* - * If we sort by symbol, the first entry is the same than - * the symbol. No need to print it otherwise it appears as - * displayed twice. - */ - if (!i++ && sort__first_dimension == SORT_SYM) - continue; - if (!printed) { - ret += callchain__fprintf_left_margin(fp, left_margin); - ret += fprintf(fp, "|\n"); - ret += callchain__fprintf_left_margin(fp, left_margin); - ret += fprintf(fp, "---"); - left_margin += 3; - printed = true; - } else - ret += callchain__fprintf_left_margin(fp, left_margin); - - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", (void *)(long)chain->ip); - - if (++entries_printed == callchain_param.print_limit) - break; - } - root = &cnode->rb_root; - } - - ret += __callchain__fprintf_graph(fp, root, total_samples, - 1, 1, left_margin); - ret += fprintf(fp, "\n"); - - return ret; -} - -static size_t __callchain__fprintf_flat(FILE *fp, - struct callchain_node *self, - u64 total_samples) -{ - struct callchain_list *chain; - size_t ret = 0; - - if (!self) - return 0; - - ret += __callchain__fprintf_flat(fp, self->parent, total_samples); - - - list_for_each_entry(chain, &self->val, list) { - if (chain->ip >= PERF_CONTEXT_MAX) - continue; - if (chain->ms.sym) - ret += fprintf(fp, " %s\n", chain->ms.sym->name); - else - ret += fprintf(fp, " %p\n", - (void *)(long)chain->ip); - } - - return ret; -} - -static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self, - u64 total_samples) -{ - size_t ret = 0; - u32 entries_printed = 0; - struct rb_node *rb_node; - struct callchain_node *chain; - - rb_node = rb_first(self); - while (rb_node) { - double percent; - - chain = rb_entry(rb_node, struct callchain_node, rb_node); - percent = chain->hit * 100.0 / total_samples; - - ret = percent_color_fprintf(fp, " %6.2f%%\n", percent); - ret += __callchain__fprintf_flat(fp, chain, total_samples); - ret += fprintf(fp, "\n"); - if (++entries_printed == callchain_param.print_limit) - break; - - rb_node = rb_next(rb_node); - } - - return ret; -} - -static size_t hist_entry_callchain__fprintf(struct hist_entry *he, - u64 total_samples, int left_margin, - FILE *fp) -{ - switch (callchain_param.mode) { - case CHAIN_GRAPH_REL: - return callchain__fprintf_graph(fp, &he->sorted_chain, he->period, - left_margin); - break; - case CHAIN_GRAPH_ABS: - return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples, - left_margin); - break; - case CHAIN_FLAT: - return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples); - break; - case CHAIN_NONE: - break; - default: - pr_err("Bad callchain mode\n"); - } - - return 0; -} - -void hists__output_recalc_col_len(struct hists *hists, int max_rows) -{ - struct rb_node *next = rb_first(&hists->entries); - struct hist_entry *n; - int row = 0; - - hists__reset_col_len(hists); - - while (next && row++ < max_rows) { - n = rb_entry(next, struct hist_entry, rb_node); - if (!n->filtered) - hists__calc_col_len(hists, n); - next = rb_next(&n->rb_node); - } -} - -static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s, - size_t size, struct hists *pair_hists, - bool show_displacement, long displacement, - bool color, u64 total_period) -{ - u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; - u64 nr_events; - const char *sep = symbol_conf.field_sep; - int ret; - - if (symbol_conf.exclude_other && !he->parent) - return 0; - - if (pair_hists) { - period = he->pair ? he->pair->period : 0; - nr_events = he->pair ? he->pair->nr_events : 0; - total = pair_hists->stats.total_period; - period_sys = he->pair ? he->pair->period_sys : 0; - period_us = he->pair ? he->pair->period_us : 0; - period_guest_sys = he->pair ? he->pair->period_guest_sys : 0; - period_guest_us = he->pair ? he->pair->period_guest_us : 0; - } else { - period = he->period; - nr_events = he->nr_events; - total = total_period; - period_sys = he->period_sys; - period_us = he->period_us; - period_guest_sys = he->period_guest_sys; - period_guest_us = he->period_guest_us; - } - - if (total) { - if (color) - ret = percent_color_snprintf(s, size, - sep ? "%.2f" : " %6.2f%%", - (period * 100.0) / total); - else - ret = scnprintf(s, size, sep ? "%.2f" : " %6.2f%%", - (period * 100.0) / total); - if (symbol_conf.show_cpu_utilization) { - ret += percent_color_snprintf(s + ret, size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_sys * 100.0) / total); - ret += percent_color_snprintf(s + ret, size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_us * 100.0) / total); - if (perf_guest) { - ret += percent_color_snprintf(s + ret, - size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_guest_sys * 100.0) / - total); - ret += percent_color_snprintf(s + ret, - size - ret, - sep ? "%.2f" : " %6.2f%%", - (period_guest_us * 100.0) / - total); - } - } - } else - ret = scnprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period); - - if (symbol_conf.show_nr_samples) { - if (sep) - ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events); - else - ret += scnprintf(s + ret, size - ret, "%11" PRIu64, nr_events); - } - - if (symbol_conf.show_total_period) { - if (sep) - ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period); - else - ret += scnprintf(s + ret, size - ret, " %12" PRIu64, period); - } - - if (pair_hists) { - char bf[32]; - double old_percent = 0, new_percent = 0, diff; - - if (total > 0) - old_percent = (period * 100.0) / total; - if (total_period > 0) - new_percent = (he->period * 100.0) / total_period; - - diff = new_percent - old_percent; - - if (fabs(diff) >= 0.01) - scnprintf(bf, sizeof(bf), "%+4.2F%%", diff); - else - scnprintf(bf, sizeof(bf), " "); - - if (sep) - ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf); - else - ret += scnprintf(s + ret, size - ret, "%11.11s", bf); - - if (show_displacement) { - if (displacement) - scnprintf(bf, sizeof(bf), "%+4ld", displacement); - else - scnprintf(bf, sizeof(bf), " "); - - if (sep) - ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf); - else - ret += scnprintf(s + ret, size - ret, "%6.6s", bf); - } - } - - return ret; -} - -int hist_entry__snprintf(struct hist_entry *he, char *s, size_t size, - struct hists *hists) -{ - const char *sep = symbol_conf.field_sep; - struct sort_entry *se; - int ret = 0; - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - ret += scnprintf(s + ret, size - ret, "%s", sep ?: " "); - ret += se->se_snprintf(he, s + ret, size - ret, - hists__col_len(hists, se->se_width_idx)); - } - - return ret; -} - -static int hist_entry__fprintf(struct hist_entry *he, size_t size, - struct hists *hists, struct hists *pair_hists, - bool show_displacement, long displacement, - u64 total_period, FILE *fp) -{ - char bf[512]; - int ret; - - if (size == 0 || size > sizeof(bf)) - size = sizeof(bf); - - ret = hist_entry__pcnt_snprintf(he, bf, size, pair_hists, - show_displacement, displacement, - true, total_period); - hist_entry__snprintf(he, bf + ret, size - ret, hists); - return fprintf(fp, "%s\n", bf); -} - -static size_t hist_entry__fprintf_callchain(struct hist_entry *he, - struct hists *hists, - u64 total_period, FILE *fp) -{ - int left_margin = 0; - - if (sort__first_dimension == SORT_COMM) { - struct sort_entry *se = list_first_entry(&hist_entry__sort_list, - typeof(*se), list); - left_margin = hists__col_len(hists, se->se_width_idx); - left_margin -= thread__comm_len(he->thread); - } - - return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); -} - -size_t hists__fprintf(struct hists *hists, struct hists *pair, - bool show_displacement, bool show_header, int max_rows, - int max_cols, FILE *fp) -{ - struct sort_entry *se; - struct rb_node *nd; - size_t ret = 0; - u64 total_period; - unsigned long position = 1; - long displacement = 0; - unsigned int width; - const char *sep = symbol_conf.field_sep; - const char *col_width = symbol_conf.col_width_list_str; - int nr_rows = 0; - - init_rem_hits(); - - if (!show_header) - goto print_entries; - - fprintf(fp, "# %s", pair ? "Baseline" : "Overhead"); - - if (symbol_conf.show_cpu_utilization) { - if (sep) { - ret += fprintf(fp, "%csys", *sep); - ret += fprintf(fp, "%cus", *sep); - if (perf_guest) { - ret += fprintf(fp, "%cguest sys", *sep); - ret += fprintf(fp, "%cguest us", *sep); - } - } else { - ret += fprintf(fp, " sys "); - ret += fprintf(fp, " us "); - if (perf_guest) { - ret += fprintf(fp, " guest sys "); - ret += fprintf(fp, " guest us "); - } - } - } - - if (symbol_conf.show_nr_samples) { - if (sep) - fprintf(fp, "%cSamples", *sep); - else - fputs(" Samples ", fp); - } - - if (symbol_conf.show_total_period) { - if (sep) - ret += fprintf(fp, "%cPeriod", *sep); - else - ret += fprintf(fp, " Period "); - } - - if (pair) { - if (sep) - ret += fprintf(fp, "%cDelta", *sep); - else - ret += fprintf(fp, " Delta "); - - if (show_displacement) { - if (sep) - ret += fprintf(fp, "%cDisplacement", *sep); - else - ret += fprintf(fp, " Displ"); - } - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - if (sep) { - fprintf(fp, "%c%s", *sep, se->se_header); - continue; - } - width = strlen(se->se_header); - if (symbol_conf.col_width_list_str) { - if (col_width) { - hists__set_col_len(hists, se->se_width_idx, - atoi(col_width)); - col_width = strchr(col_width, ','); - if (col_width) - ++col_width; - } - } - if (!hists__new_col_len(hists, se->se_width_idx, width)) - width = hists__col_len(hists, se->se_width_idx); - fprintf(fp, " %*s", width, se->se_header); - } - - fprintf(fp, "\n"); - if (max_rows && ++nr_rows >= max_rows) - goto out; - - if (sep) - goto print_entries; - - fprintf(fp, "# ........"); - if (symbol_conf.show_cpu_utilization) - fprintf(fp, " ....... ......."); - if (symbol_conf.show_nr_samples) - fprintf(fp, " .........."); - if (symbol_conf.show_total_period) - fprintf(fp, " ............"); - if (pair) { - fprintf(fp, " .........."); - if (show_displacement) - fprintf(fp, " ....."); - } - list_for_each_entry(se, &hist_entry__sort_list, list) { - unsigned int i; - - if (se->elide) - continue; - - fprintf(fp, " "); - width = hists__col_len(hists, se->se_width_idx); - if (width == 0) - width = strlen(se->se_header); - for (i = 0; i < width; i++) - fprintf(fp, "."); - } - - fprintf(fp, "\n"); - if (max_rows && ++nr_rows >= max_rows) - goto out; - - fprintf(fp, "#\n"); - if (max_rows && ++nr_rows >= max_rows) - goto out; - -print_entries: - total_period = hists->stats.total_period; - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - - if (h->filtered) - continue; - - if (show_displacement) { - if (h->pair != NULL) - displacement = ((long)h->pair->position - - (long)position); - else - displacement = 0; - ++position; - } - ret += hist_entry__fprintf(h, max_cols, hists, pair, show_displacement, - displacement, total_period, fp); - - if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, hists, total_period, fp); - if (max_rows && ++nr_rows >= max_rows) - goto out; - - if (h->ms.map == NULL && verbose > 1) { - __map_groups__fprintf_maps(&h->thread->mg, - MAP__FUNCTION, verbose, fp); - fprintf(fp, "%.10s end\n", graph_dotted_line); - } - } -out: - free(rem_sq_bracket); - - return ret; -} - -/* - * See hists__fprintf to match the column widths - */ -unsigned int hists__sort_list_width(struct hists *hists) -{ - struct sort_entry *se; - int ret = 9; /* total % */ - - if (symbol_conf.show_cpu_utilization) { - ret += 7; /* count_sys % */ - ret += 6; /* count_us % */ - if (perf_guest) { - ret += 13; /* count_guest_sys % */ - ret += 12; /* count_guest_us % */ - } - } - - if (symbol_conf.show_nr_samples) - ret += 11; - - if (symbol_conf.show_total_period) - ret += 13; - - list_for_each_entry(se, &hist_entry__sort_list, list) - if (!se->elide) - ret += 2 + hists__col_len(hists, se->se_width_idx); - - if (verbose) /* Addr + origin */ - ret += 3 + BITS_PER_LONG / 4; - - return ret; -} - static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { @@ -1342,25 +695,3 @@ void hists__inc_nr_events(struct hists *hists, u32 type) ++hists->stats.nr_events[0]; ++hists->stats.nr_events[type]; } - -size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) -{ - int i; - size_t ret = 0; - - for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { - const char *name; - - if (hists->stats.nr_events[i] == 0) - continue; - - name = perf_event__name(i); - if (!strcmp(name, "UNKNOWN")) - continue; - - ret += fprintf(fp, "%16s events: %10d\n", name, - hists->stats.nr_events[i]); - } - - return ret; -} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 0b096c27a419..f011ad4756e8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -75,8 +75,8 @@ struct hist_entry *__hists__add_entry(struct hists *self, struct symbol *parent, u64 period); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); -int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size, - struct hists *hists); +int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size, + struct hists *hists); void hist_entry__free(struct hist_entry *); struct hist_entry *__hists__add_branch_entry(struct hists *self, @@ -112,25 +112,66 @@ void hists__filter_by_symbol(struct hists *hists); u16 hists__col_len(struct hists *self, enum hist_column col); void hists__set_col_len(struct hists *self, enum hist_column col, u16 len); bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); +void hists__reset_col_len(struct hists *hists); +void hists__calc_col_len(struct hists *hists, struct hist_entry *he); + +struct perf_hpp { + char *buf; + size_t size; + u64 total_period; + const char *sep; + long displacement; + void *ptr; +}; + +struct perf_hpp_fmt { + bool cond; + int (*header)(struct perf_hpp *hpp); + int (*width)(struct perf_hpp *hpp); + int (*color)(struct perf_hpp *hpp, struct hist_entry *he); + int (*entry)(struct perf_hpp *hpp, struct hist_entry *he); +}; + +extern struct perf_hpp_fmt perf_hpp__format[]; + +enum { + PERF_HPP__OVERHEAD, + PERF_HPP__OVERHEAD_SYS, + PERF_HPP__OVERHEAD_US, + PERF_HPP__OVERHEAD_GUEST_SYS, + PERF_HPP__OVERHEAD_GUEST_US, + PERF_HPP__SAMPLES, + PERF_HPP__PERIOD, + PERF_HPP__DELTA, + PERF_HPP__DISPL, + + PERF_HPP__MAX_INDEX +}; + +void perf_hpp__init(bool need_pair, bool show_displacement); +int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, + bool color); struct perf_evlist; #ifdef NO_NEWT_SUPPORT static inline -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used, - const char *help __used, - void(*timer)(void *arg) __used, - void *arg __used, - int refresh __used) +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, + const char *help __maybe_unused, + void(*timer)(void *arg) __maybe_unused, + void *arg __maybe_unused, + int refresh __maybe_unused) { return 0; } -static inline int hist_entry__tui_annotate(struct hist_entry *self __used, - int evidx __used, - void(*timer)(void *arg) __used, - void *arg __used, - int delay_secs __used) +static inline int hist_entry__tui_annotate(struct hist_entry *self + __maybe_unused, + int evidx __maybe_unused, + void(*timer)(void *arg) + __maybe_unused, + void *arg __maybe_unused, + int delay_secs __maybe_unused) { return 0; } @@ -148,11 +189,11 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, #ifdef NO_GTK2_SUPPORT static inline -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __used, - const char *help __used, - void(*timer)(void *arg) __used, - void *arg __used, - int refresh __used) +int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, + const char *help __maybe_unused, + void(*timer)(void *arg) __maybe_unused, + void *arg __maybe_unused, + int refresh __maybe_unused) { return 0; } diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index 587a230d2075..a55d8cf083c9 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -5,6 +5,10 @@ #include <linux/compiler.h> #include <asm/hweight.h> +#ifndef __WORDSIZE +#define __WORDSIZE (__SIZEOF_LONG__ * 8) +#endif + #define BITS_PER_LONG __WORDSIZE #define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h index 547628e97f3d..96b919dae11c 100644 --- a/tools/perf/util/include/linux/compiler.h +++ b/tools/perf/util/include/linux/compiler.h @@ -9,6 +9,13 @@ #define __attribute_const__ #endif -#define __used __attribute__((__unused__)) +#ifndef __maybe_unused +#define __maybe_unused __attribute__((unused)) +#endif +#define __packed __attribute__((__packed__)) + +#ifndef __force +#define __force +#endif #endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index b6842c1d02a8..d8c927c868ee 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -8,8 +8,8 @@ #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) -#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1) -#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask)) +#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) +#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) #ifndef offsetof #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) @@ -46,9 +46,22 @@ _min1 < _min2 ? _min1 : _min2; }) #endif +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + #ifndef BUG_ON +#ifdef NDEBUG +#define BUG_ON(cond) do { if (cond) {} } while (0) +#else #define BUG_ON(cond) assert(!(cond)) #endif +#endif /* * Both need more care to handle endianness diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h new file mode 100644 index 000000000000..58b64ed4da12 --- /dev/null +++ b/tools/perf/util/include/linux/magic.h @@ -0,0 +1,12 @@ +#ifndef _PERF_LINUX_MAGIC_H_ +#define _PERF_LINUX_MAGIC_H_ + +#ifndef DEBUGFS_MAGIC +#define DEBUGFS_MAGIC 0x64626720 +#endif + +#ifndef SYSFS_MAGIC +#define SYSFS_MAGIC 0x62656572 +#endif + +#endif diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h index 7a243a143037..2a030c5af3aa 100644 --- a/tools/perf/util/include/linux/rbtree.h +++ b/tools/perf/util/include/linux/rbtree.h @@ -1 +1,2 @@ +#include <stdbool.h> #include "../../../../include/linux/rbtree.h" diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 3b2f5900276f..6f19c548ecc0 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1 +1,3 @@ #include <string.h> + +void *memdup(const void *src, size_t len); diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h index 12de3b8112f9..eb464786c084 100644 --- a/tools/perf/util/include/linux/types.h +++ b/tools/perf/util/include/linux/types.h @@ -3,6 +3,14 @@ #include <asm/types.h> +#ifndef __bitwise +#define __bitwise +#endif + +#ifndef __le32 +typedef __u32 __bitwise __le32; +#endif + #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c index fd530dced9cb..9d0740024ba8 100644 --- a/tools/perf/util/intlist.c +++ b/tools/perf/util/intlist.c @@ -11,7 +11,7 @@ #include "intlist.h" -static struct rb_node *intlist__node_new(struct rblist *rblist __used, +static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused, const void *entry) { int i = (int)((long)entry); @@ -31,7 +31,7 @@ static void int_node__delete(struct int_node *ilist) free(ilist); } -static void intlist__node_delete(struct rblist *rblist __used, +static void intlist__node_delete(struct rblist *rblist __maybe_unused, struct rb_node *rb_node) { struct int_node *node = container_of(rb_node, struct int_node, rb_node); @@ -52,9 +52,9 @@ int intlist__add(struct intlist *ilist, int i) return rblist__add_node(&ilist->rblist, (void *)((long)i)); } -void intlist__remove(struct intlist *ilist __used, struct int_node *node) +void intlist__remove(struct intlist *ilist, struct int_node *node) { - int_node__delete(node); + rblist__remove_node(&ilist->rblist, &node->rb_node); } struct int_node *intlist__find(struct intlist *ilist, int i) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index cc33486ad9e2..ead5316b3f89 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -9,6 +9,7 @@ #include "map.h" #include "thread.h" #include "strlist.h" +#include "vdso.h" const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -23,7 +24,6 @@ static inline int is_anon_memory(const char *filename) static inline int is_no_dso_memory(const char *filename) { return !strcmp(filename, "[stack]") || - !strcmp(filename, "[vdso]") || !strcmp(filename, "[heap]"); } @@ -52,9 +52,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (self != NULL) { char newfilename[PATH_MAX]; struct dso *dso; - int anon, no_dso; + int anon, no_dso, vdso; anon = is_anon_memory(filename); + vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); if (anon) { @@ -62,7 +63,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, filename = newfilename; } - dso = __dsos__findnew(dsos__list, filename); + if (vdso) { + pgoff = 0; + dso = vdso__dso_findnew(dsos__list); + } else + dso = __dsos__findnew(dsos__list, filename); + if (dso == NULL) goto out_delete; @@ -86,6 +92,25 @@ out_delete: return NULL; } +/* + * Constructor variant for modules (where we know from /proc/modules where + * they are loaded) and for vmlinux, where only after we load all the + * symbols we'll know where it starts and ends. + */ +struct map *map__new2(u64 start, struct dso *dso, enum map_type type) +{ + struct map *map = calloc(1, (sizeof(*map) + + (dso->kernel ? sizeof(struct kmap) : 0))); + if (map != NULL) { + /* + * ->end will be filled after we load all the symbols + */ + map__init(map, type, start, 0, 0, dso); + } + + return map; +} + void map__delete(struct map *self) { free(self); @@ -137,6 +162,7 @@ int map__load(struct map *self, symbol_filter_t filter) pr_warning(", continuing without symbols\n"); return -1; } else if (nr == 0) { +#ifndef NO_LIBELF_SUPPORT const size_t len = strlen(name); const size_t real_len = len - sizeof(DSO__DELETED); @@ -149,7 +175,7 @@ int map__load(struct map *self, symbol_filter_t filter) pr_warning("no symbols found in %s, maybe install " "a debug package?\n", name); } - +#endif return -1; } /* @@ -217,15 +243,14 @@ size_t map__fprintf(struct map *self, FILE *fp) size_t map__fprintf_dsoname(struct map *map, FILE *fp) { - const char *dsoname; + const char *dsoname = "[unknown]"; if (map && map->dso && (map->dso->name || map->dso->long_name)) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; else if (map->dso->name) dsoname = map->dso->name; - } else - dsoname = "[unknown]"; + } return fprintf(fp, "%s", dsoname); } @@ -242,14 +267,6 @@ u64 map__rip_2objdump(struct map *map, u64 rip) return addr; } -u64 map__objdump_2ip(struct map *map, u64 addr) -{ - u64 ip = map->dso->adjust_symbols ? - addr : - map->unmap_ip(map, addr); /* RIP -> IP */ - return ip; -} - void map_groups__init(struct map_groups *mg) { int i; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 03a1e9b08b21..d2250fc97e25 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -96,7 +96,7 @@ static inline u64 map__unmap_ip(struct map *map, u64 ip) return ip + map->start - map->pgoff; } -static inline u64 identity__map_ip(struct map *map __used, u64 ip) +static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) { return ip; } @@ -104,7 +104,6 @@ static inline u64 identity__map_ip(struct map *map __used, u64 ip) /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); -u64 map__objdump_2ip(struct map *map, u64 addr); struct symbol; @@ -115,6 +114,7 @@ void map__init(struct map *self, enum map_type type, struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, enum map_type type); +struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *self); struct map *map__clone(struct map *self); int map__overlap(struct map *l, struct map *r); @@ -157,9 +157,12 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid); void machine__exit(struct machine *self); void machine__delete(struct machine *self); +struct perf_evsel; +struct perf_sample; int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, struct thread *thread, - struct ip_callchain *chain, + struct perf_sample *sample, struct symbol **parent); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c index 607dd290b319..28c18d1d52c3 100644 --- a/tools/perf/util/parse-events-test.c +++ b/tools/perf/util/parse-events-test.c @@ -18,8 +18,7 @@ do { \ static int test__checkevent_tracepoint(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); @@ -48,8 +47,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist) static int test__checkevent_raw(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); @@ -59,8 +57,7 @@ static int test__checkevent_raw(struct perf_evlist *evlist) static int test__checkevent_numeric(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); @@ -70,8 +67,7 @@ static int test__checkevent_numeric(struct perf_evlist *evlist) static int test__checkevent_symbolic_name(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); @@ -82,8 +78,7 @@ static int test__checkevent_symbolic_name(struct perf_evlist *evlist) static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); @@ -100,8 +95,7 @@ static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist) static int test__checkevent_symbolic_alias(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type); @@ -112,8 +106,7 @@ static int test__checkevent_symbolic_alias(struct perf_evlist *evlist) static int test__checkevent_genhw(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type); @@ -123,8 +116,7 @@ static int test__checkevent_genhw(struct perf_evlist *evlist) static int test__checkevent_breakpoint(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); @@ -138,8 +130,7 @@ static int test__checkevent_breakpoint(struct perf_evlist *evlist) static int test__checkevent_breakpoint_x(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); @@ -152,8 +143,7 @@ static int test__checkevent_breakpoint_x(struct perf_evlist *evlist) static int test__checkevent_breakpoint_r(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", @@ -168,8 +158,7 @@ static int test__checkevent_breakpoint_r(struct perf_evlist *evlist) static int test__checkevent_breakpoint_w(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", @@ -184,8 +173,7 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist) static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", @@ -200,8 +188,7 @@ static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist) static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); @@ -232,8 +219,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist) static int test__checkevent_raw_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); @@ -245,8 +231,7 @@ static int test__checkevent_raw_modifier(struct perf_evlist *evlist) static int test__checkevent_numeric_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); @@ -258,8 +243,7 @@ static int test__checkevent_numeric_modifier(struct perf_evlist *evlist) static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); @@ -271,8 +255,7 @@ static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist) static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); @@ -282,8 +265,7 @@ static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist) static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); @@ -293,8 +275,7 @@ static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist) static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); @@ -306,8 +287,7 @@ static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist) static int test__checkevent_genhw_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); @@ -319,75 +299,71 @@ static int test__checkevent_genhw_modifier(struct perf_evlist *evlist) static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u")); + !strcmp(perf_evsel__name(evsel), "mem:0:u")); return test__checkevent_breakpoint(evlist); } static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k")); + !strcmp(perf_evsel__name(evsel), "mem:0:x:k")); return test__checkevent_breakpoint_x(evlist); } static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp")); + !strcmp(perf_evsel__name(evsel), "mem:0:r:hp")); return test__checkevent_breakpoint_r(evlist); } static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up")); + !strcmp(perf_evsel__name(evsel), "mem:0:w:up")); return test__checkevent_breakpoint_w(evlist); } static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp")); + !strcmp(perf_evsel__name(evsel), "mem:0:rw:kp")); return test__checkevent_breakpoint_rw(evlist); } @@ -395,8 +371,7 @@ static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist) static int test__checkevent_pmu(struct perf_evlist *evlist) { - struct perf_evsel *evsel = list_entry(evlist->entries.next, - struct perf_evsel, node); + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); @@ -410,12 +385,11 @@ static int test__checkevent_pmu(struct perf_evlist *evlist) static int test__checkevent_list(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); /* r1 */ - evsel = list_entry(evlist->entries.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1); @@ -426,7 +400,7 @@ static int test__checkevent_list(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); /* syscalls:sys_enter_open:k */ - evsel = list_entry(evsel->node.next, struct perf_evsel, node); + evsel = perf_evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); @@ -437,7 +411,7 @@ static int test__checkevent_list(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); /* 1:1:hp */ - evsel = list_entry(evsel->node.next, struct perf_evsel, node); + evsel = perf_evsel__next(evsel); TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); @@ -450,22 +424,21 @@ static int test__checkevent_list(struct perf_evlist *evlist) static int test__checkevent_pmu_name(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel = perf_evlist__first(evlist); /* cpu/config=1,name=krava/u */ - evsel = list_entry(evlist->entries.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava")); /* cpu/config=2/u" */ - evsel = list_entry(evsel->node.next, struct perf_evsel, node); + evsel = perf_evsel__next(evsel); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config); TEST_ASSERT_VAL("wrong name", - !strcmp(perf_evsel__name(evsel), "raw 0x2:u")); + !strcmp(perf_evsel__name(evsel), "cpu/config=2/u")); return 0; } @@ -513,6 +486,280 @@ static int test__checkterms_simple(struct list_head *terms) return 0; } +static int test__group1(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + + /* instructions:k */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + /* cycles:upp */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + return 0; +} + +static int test__group2(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + + /* faults + :ku modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + /* cache-references + :u modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_REFERENCES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + /* cycles:k */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + return 0; +} + +static int test__group3(struct perf_evlist *evlist __maybe_unused) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + + /* group1 syscalls:sys_enter_open:H */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong sample_type", + PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); + TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong group name", + !strcmp(leader->group_name, "group1")); + + /* group1 cycles:kppp */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + + /* group2 cycles + G modifier */ + evsel = leader = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong group name", + !strcmp(leader->group_name, "group2")); + + /* group2 1:3 + G modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 3 == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + /* instructions:u */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + return 0; +} + +static int test__group4(struct perf_evlist *evlist __maybe_unused) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + + /* cycles:u + p */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + /* instructions:kp + p */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + return 0; +} + +static int test__group5(struct perf_evlist *evlist __maybe_unused) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + + /* cycles + G */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + /* instructions + G */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + /* cycles:G */ + evsel = leader = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + /* instructions:G */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + + /* cycles */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + + return 0; +} + struct test__event_st { const char *name; __u32 type; @@ -632,6 +879,26 @@ static struct test__event_st test__events[] = { .name = "mem:0:rw:kp", .check = test__checkevent_breakpoint_rw_modifier, }, + [28] = { + .name = "{instructions:k,cycles:upp}", + .check = test__group1, + }, + [29] = { + .name = "{faults:k,cache-references}:u,cycles:k", + .check = test__group2, + }, + [30] = { + .name = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u", + .check = test__group3, + }, + [31] = { + .name = "{cycles:u,instructions:kp}:p", + .check = test__group4, + }, + [32] = { + .name = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles", + .check = test__group5, + }, }; static struct test__event_st test__events_pmu[] = { @@ -658,9 +925,6 @@ static struct test__term test__terms[] = { }, }; -#define TEST__TERMS_CNT (sizeof(test__terms) / \ - sizeof(struct test__term)) - static int test_event(struct test__event_st *e) { struct perf_evlist *evlist; @@ -685,19 +949,19 @@ static int test_event(struct test__event_st *e) static int test_events(struct test__event_st *events, unsigned cnt) { - int ret = 0; + int ret1, ret2 = 0; unsigned i; for (i = 0; i < cnt; i++) { struct test__event_st *e = &events[i]; pr_debug("running test %d '%s'\n", i, e->name); - ret = test_event(e); - if (ret) - break; + ret1 = test_event(e); + if (ret1) + ret2 = ret1; } - return ret; + return ret2; } static int test_term(struct test__term *t) @@ -758,13 +1022,13 @@ static int test_pmu(void) int parse_events__test(void) { - int ret; + int ret1, ret2 = 0; #define TEST_EVENTS(tests) \ do { \ - ret = test_events(tests, ARRAY_SIZE(tests)); \ - if (ret) \ - return ret; \ + ret1 = test_events(tests, ARRAY_SIZE(tests)); \ + if (!ret2) \ + ret2 = ret1; \ } while (0) TEST_EVENTS(test__events); @@ -772,5 +1036,9 @@ do { \ if (test_pmu()) TEST_EVENTS(test__events_pmu); - return test_terms(test__terms, ARRAY_SIZE(test__terms)); + ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms)); + if (!ret2) + ret2 = ret1; + + return ret2; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 74a5af4d33ec..aed38e4b9dfa 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -239,8 +239,11 @@ const char *event_type(int type) return "unknown"; } -static int add_event(struct list_head **_list, int *idx, - struct perf_event_attr *attr, char *name) + + +static int __add_event(struct list_head **_list, int *idx, + struct perf_event_attr *attr, + char *name, struct cpu_map *cpus) { struct perf_evsel *evsel; struct list_head *list = *_list; @@ -260,6 +263,7 @@ static int add_event(struct list_head **_list, int *idx, return -ENOMEM; } + evsel->cpus = cpus; if (name) evsel->name = strdup(name); list_add_tail(&evsel->node, list); @@ -267,6 +271,12 @@ static int add_event(struct list_head **_list, int *idx, return 0; } +static int add_event(struct list_head **_list, int *idx, + struct perf_event_attr *attr, char *name) +{ + return __add_event(_list, idx, attr, name, NULL); +} + static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) { int i, j; @@ -308,7 +318,7 @@ int parse_events_add_cache(struct list_head **list, int *idx, for (i = 0; (i < 2) && (op_result[i]); i++) { char *str = op_result[i]; - snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str); + n += snprintf(name + n, MAX_NAME_LEN - n, "-%s", str); if (cache_op == -1) { cache_op = parse_aliases(str, perf_evsel__hw_cache_op, @@ -346,42 +356,28 @@ int parse_events_add_cache(struct list_head **list, int *idx, return add_event(list, idx, &attr, name); } -static int add_tracepoint(struct list_head **list, int *idx, +static int add_tracepoint(struct list_head **listp, int *idx, char *sys_name, char *evt_name) { - struct perf_event_attr attr; - char name[MAX_NAME_LEN]; - char evt_path[MAXPATHLEN]; - char id_buf[4]; - u64 id; - int fd; - - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, - sys_name, evt_name); - - fd = open(evt_path, O_RDONLY); - if (fd < 0) - return -1; + struct perf_evsel *evsel; + struct list_head *list = *listp; - if (read(fd, id_buf, sizeof(id_buf)) < 0) { - close(fd); - return -1; + if (!list) { + list = malloc(sizeof(*list)); + if (!list) + return -ENOMEM; + INIT_LIST_HEAD(list); } - close(fd); - id = atoll(id_buf); - - memset(&attr, 0, sizeof(attr)); - attr.config = id; - attr.type = PERF_TYPE_TRACEPOINT; - attr.sample_type |= PERF_SAMPLE_RAW; - attr.sample_type |= PERF_SAMPLE_TIME; - attr.sample_type |= PERF_SAMPLE_CPU; - attr.sample_type |= PERF_SAMPLE_PERIOD; - attr.sample_period = 1; + evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++); + if (!evsel) { + free(list); + return -ENOMEM; + } - snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name); - return add_event(list, idx, &attr, name); + list_add_tail(&evsel->node, list); + *listp = list; + return 0; } static int add_tracepoint_multi(struct list_head **list, int *idx, @@ -551,7 +547,7 @@ static int config_attr(struct perf_event_attr *attr, } int parse_events_add_numeric(struct list_head **list, int *idx, - unsigned long type, unsigned long config, + u32 type, u64 config, struct list_head *head_config) { struct perf_event_attr attr; @@ -607,8 +603,23 @@ int parse_events_add_pmu(struct list_head **list, int *idx, if (perf_pmu__config(pmu, &attr, head_config)) return -EINVAL; - return add_event(list, idx, &attr, - pmu_event_name(head_config)); + return __add_event(list, idx, &attr, pmu_event_name(head_config), + pmu->cpus); +} + +int parse_events__modifier_group(struct list_head *list, + char *event_mod) +{ + return parse_events__modifier_event(list, event_mod, true); +} + +void parse_events__set_leader(char *name, struct list_head *list) +{ + struct perf_evsel *leader; + + __perf_evlist__set_leader(list); + leader = list_entry(list->next, struct perf_evsel, node); + leader->group_name = name ? strdup(name) : NULL; } void parse_events_update_lists(struct list_head *list_event, @@ -616,21 +627,45 @@ void parse_events_update_lists(struct list_head *list_event, { /* * Called for single event definition. Update the - * 'all event' list, and reinit the 'signle event' + * 'all event' list, and reinit the 'single event' * list, for next event definition. */ list_splice_tail(list_event, list_all); free(list_event); } -int parse_events_modifier(struct list_head *list, char *str) +struct event_modifier { + int eu; + int ek; + int eh; + int eH; + int eG; + int precise; + int exclude_GH; +}; + +static int get_event_modifier(struct event_modifier *mod, char *str, + struct perf_evsel *evsel) { - struct perf_evsel *evsel; - int exclude = 0, exclude_GH = 0; - int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0; + int eu = evsel ? evsel->attr.exclude_user : 0; + int ek = evsel ? evsel->attr.exclude_kernel : 0; + int eh = evsel ? evsel->attr.exclude_hv : 0; + int eH = evsel ? evsel->attr.exclude_host : 0; + int eG = evsel ? evsel->attr.exclude_guest : 0; + int precise = evsel ? evsel->attr.precise_ip : 0; - if (str == NULL) - return 0; + int exclude = eu | ek | eh; + int exclude_GH = evsel ? evsel->exclude_GH : 0; + + /* + * We are here for group and 'GH' was not set as event + * modifier and whatever event/group modifier override + * default 'GH' setup. + */ + if (evsel && !exclude_GH) + eH = eG = 0; + + memset(mod, 0, sizeof(*mod)); while (*str) { if (*str == 'u') { @@ -674,13 +709,51 @@ int parse_events_modifier(struct list_head *list, char *str) if (precise > 3) return -EINVAL; + mod->eu = eu; + mod->ek = ek; + mod->eh = eh; + mod->eH = eH; + mod->eG = eG; + mod->precise = precise; + mod->exclude_GH = exclude_GH; + return 0; +} + +int parse_events__modifier_event(struct list_head *list, char *str, bool add) +{ + struct perf_evsel *evsel; + struct event_modifier mod; + + if (str == NULL) + return 0; + + if (!add && get_event_modifier(&mod, str, NULL)) + return -EINVAL; + list_for_each_entry(evsel, list, node) { - evsel->attr.exclude_user = eu; - evsel->attr.exclude_kernel = ek; - evsel->attr.exclude_hv = eh; - evsel->attr.precise_ip = precise; - evsel->attr.exclude_host = eH; - evsel->attr.exclude_guest = eG; + + if (add && get_event_modifier(&mod, str, evsel)) + return -EINVAL; + + evsel->attr.exclude_user = mod.eu; + evsel->attr.exclude_kernel = mod.ek; + evsel->attr.exclude_hv = mod.eh; + evsel->attr.precise_ip = mod.precise; + evsel->attr.exclude_host = mod.eH; + evsel->attr.exclude_guest = mod.eG; + evsel->exclude_GH = mod.exclude_GH; + } + + return 0; +} + +int parse_events_name(struct list_head *list, char *name) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, list, node) { + if (!evsel->name) + evsel->name = strdup(name); } return 0; @@ -730,7 +803,8 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) +int parse_events(struct perf_evlist *evlist, const char *str, + int unset __maybe_unused) { struct parse_events_data__events data = { .list = LIST_HEAD_INIT(data.list), @@ -756,20 +830,20 @@ int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) } int parse_events_option(const struct option *opt, const char *str, - int unset __used) + int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; return parse_events(evlist, str, unset); } int parse_filter(const struct option *opt, const char *str, - int unset __used) + int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; struct perf_evsel *last = NULL; if (evlist->nr_entries > 0) - last = list_entry(evlist->entries.prev, struct perf_evsel, node); + last = perf_evlist__last(evlist); if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, @@ -799,7 +873,8 @@ static const char * const event_type_descriptors[] = { * Print the events from <debugfs_mount_point>/tracing/events */ -void print_tracepoint_events(const char *subsys_glob, const char *event_glob) +void print_tracepoint_events(const char *subsys_glob, const char *event_glob, + bool name_only) { DIR *sys_dir, *evt_dir; struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; @@ -829,6 +904,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob) !strglobmatch(evt_dirent.d_name, event_glob)) continue; + if (name_only) { + printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name); + continue; + } + snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); printf(" %-50s [%s]\n", evt_path, @@ -906,7 +986,7 @@ void print_events_type(u8 type) __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); } -int print_hwcache_events(const char *event_glob) +int print_hwcache_events(const char *event_glob, bool name_only) { unsigned int type, op, i, printed = 0; char name[64]; @@ -923,8 +1003,11 @@ int print_hwcache_events(const char *event_glob) if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; - printf(" %-50s [%s]\n", name, - event_type_descriptors[PERF_TYPE_HW_CACHE]); + if (name_only) + printf("%s ", name); + else + printf(" %-50s [%s]\n", name, + event_type_descriptors[PERF_TYPE_HW_CACHE]); ++printed; } } @@ -934,7 +1017,8 @@ int print_hwcache_events(const char *event_glob) } static void print_symbol_events(const char *event_glob, unsigned type, - struct event_symbol *syms, unsigned max) + struct event_symbol *syms, unsigned max, + bool name_only) { unsigned i, printed = 0; char name[MAX_NAME_LEN]; @@ -946,6 +1030,11 @@ static void print_symbol_events(const char *event_glob, unsigned type, (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; + if (name_only) { + printf("%s ", syms->symbol); + continue; + } + if (strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else @@ -963,39 +1052,42 @@ static void print_symbol_events(const char *event_glob, unsigned type, /* * Print the help text for the event symbols: */ -void print_events(const char *event_glob) +void print_events(const char *event_glob, bool name_only) { - - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); + if (!name_only) { + printf("\n"); + printf("List of pre-defined events (to be used in -e):\n"); + } print_symbol_events(event_glob, PERF_TYPE_HARDWARE, - event_symbols_hw, PERF_COUNT_HW_MAX); + event_symbols_hw, PERF_COUNT_HW_MAX, name_only); print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, - event_symbols_sw, PERF_COUNT_SW_MAX); + event_symbols_sw, PERF_COUNT_SW_MAX, name_only); - print_hwcache_events(event_glob); + print_hwcache_events(event_glob, name_only); if (event_glob != NULL) return; - printf("\n"); - printf(" %-50s [%s]\n", - "rNNN", - event_type_descriptors[PERF_TYPE_RAW]); - printf(" %-50s [%s]\n", - "cpu/t1=v1[,t2=v2,t3 ...]/modifier", - event_type_descriptors[PERF_TYPE_RAW]); - printf(" (see 'perf list --help' on how to encode it)\n"); - printf("\n"); - - printf(" %-50s [%s]\n", - "mem:<addr>[:access]", + if (!name_only) { + printf("\n"); + printf(" %-50s [%s]\n", + "rNNN", + event_type_descriptors[PERF_TYPE_RAW]); + printf(" %-50s [%s]\n", + "cpu/t1=v1[,t2=v2,t3 ...]/modifier", + event_type_descriptors[PERF_TYPE_RAW]); + printf(" (see 'perf list --help' on how to encode it)\n"); + printf("\n"); + + printf(" %-50s [%s]\n", + "mem:<addr>[:access]", event_type_descriptors[PERF_TYPE_BREAKPOINT]); - printf("\n"); + printf("\n"); + } - print_tracepoint_events(NULL, NULL); + print_tracepoint_events(NULL, NULL, name_only); } int parse_events__is_hardcoded_term(struct parse_events__term *term) @@ -1005,7 +1097,7 @@ int parse_events__is_hardcoded_term(struct parse_events__term *term) static int new_term(struct parse_events__term **_term, int type_val, int type_term, char *config, - char *str, long num) + char *str, u64 num) { struct parse_events__term *term; @@ -1034,7 +1126,7 @@ static int new_term(struct parse_events__term **_term, int type_val, } int parse_events__term_num(struct parse_events__term **term, - int type_term, char *config, long num) + int type_term, char *config, u64 num) { return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, config, NULL, num); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index ee9c218a193c..c356e443448d 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -55,7 +55,7 @@ struct parse_events__term { char *config; union { char *str; - long num; + u64 num; } val; int type_val; int type_term; @@ -73,17 +73,19 @@ struct parse_events_data__terms { int parse_events__is_hardcoded_term(struct parse_events__term *term); int parse_events__term_num(struct parse_events__term **_term, - int type_term, char *config, long num); + int type_term, char *config, u64 num); int parse_events__term_str(struct parse_events__term **_term, int type_term, char *config, char *str); int parse_events__term_clone(struct parse_events__term **new, struct parse_events__term *term); void parse_events__free_terms(struct list_head *terms); -int parse_events_modifier(struct list_head *list, char *str); +int parse_events__modifier_event(struct list_head *list, char *str, bool add); +int parse_events__modifier_group(struct list_head *list, char *event_mod); +int parse_events_name(struct list_head *list, char *name); int parse_events_add_tracepoint(struct list_head **list, int *idx, char *sys, char *event); int parse_events_add_numeric(struct list_head **list, int *idx, - unsigned long type, unsigned long config, + u32 type, u64 config, struct list_head *head_config); int parse_events_add_cache(struct list_head **list, int *idx, char *type, char *op_result1, char *op_result2); @@ -91,15 +93,17 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, void *ptr, char *type); int parse_events_add_pmu(struct list_head **list, int *idx, char *pmu , struct list_head *head_config); +void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_error(void *data, void *scanner, char const *msg); int parse_events__test(void); -void print_events(const char *event_glob); +void print_events(const char *event_glob, bool name_only); void print_events_type(u8 type); -void print_tracepoint_events(const char *subsys_glob, const char *event_glob); -int print_hwcache_events(const char *event_glob); +void print_tracepoint_events(const char *subsys_glob, const char *event_glob, + bool name_only); +int print_hwcache_events(const char *event_glob, bool name_only); extern int is_valid_tracepoint(const char *event_string); extern int valid_debugfs_mount(const char *debugfs); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 384ca74c6b22..c87efc12579d 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -15,10 +15,10 @@ YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); static int __value(YYSTYPE *yylval, char *str, int base, int token) { - long num; + u64 num; errno = 0; - num = strtoul(str, NULL, base); + num = strtoull(str, NULL, base); if (errno) return PE_ERROR; @@ -70,6 +70,12 @@ static int term(yyscan_t scanner, int type) %} %x mem +%s config +%x event + +group [^,{}/]*[{][^}]*[}][^,{}/]* +event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* +event [^,{}/]+ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ @@ -84,7 +90,13 @@ modifier_bp [rwx]{1,3} { int start_token; - start_token = (int) parse_events_get_extra(yyscanner); + start_token = parse_events_get_extra(yyscanner); + + if (start_token == PE_START_TERMS) + BEGIN(config); + else if (start_token == PE_START_EVENTS) + BEGIN(event); + if (start_token) { parse_events_set_extra(NULL, yyscanner); return start_token; @@ -92,6 +104,26 @@ modifier_bp [rwx]{1,3} } %} +<event>{ + +{group} { + BEGIN(INITIAL); yyless(0); + } + +{event_pmu} | +{event} { + str(yyscanner, PE_EVENT_NAME); + BEGIN(INITIAL); yyless(0); + return PE_EVENT_NAME; + } + +. | +<<EOF>> { + BEGIN(INITIAL); yyless(0); + } + +} + cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } @@ -127,18 +159,16 @@ speculative-read|speculative-load | refs|Reference|ops|access | misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } - /* - * These are event config hardcoded term names to be specified - * within xxx/.../ syntax. So far we dont clash with other names, - * so we can put them here directly. In case the we have a conflict - * in future, this needs to go into '//' condition block. - */ +<config>{ config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +, { return ','; } +"/" { BEGIN(INITIAL); return '/'; } +} mem: { BEGIN(mem); return PE_PREFIX_MEM; } r{num_raw_hex} { return raw(yyscanner); } @@ -147,10 +177,12 @@ r{num_raw_hex} { return raw(yyscanner); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {name} { return str(yyscanner, PE_NAME); } -"/" { return '/'; } +"/" { BEGIN(config); return '/'; } - { return '-'; } -, { return ','; } +, { BEGIN(event); return ','; } : { return ':'; } +"{" { BEGIN(event); return '{'; } +"}" { return '}'; } = { return '='; } \n { } @@ -175,7 +207,7 @@ r{num_raw_hex} { return raw(yyscanner); } %% -int parse_events_wrap(void *scanner __used) +int parse_events_wrap(void *scanner __maybe_unused) { return 1; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 2bc5fbff2b5d..cd88209e3c58 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -27,10 +27,11 @@ do { \ %token PE_START_EVENTS PE_START_TERMS %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM +%token PE_EVENT_NAME %token PE_NAME %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT -%token PE_PREFIX_MEM PE_PREFIX_RAW +%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW @@ -42,6 +43,7 @@ do { \ %type <str> PE_NAME_CACHE_OP_RESULT %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP +%type <str> PE_EVENT_NAME %type <num> value_sym %type <head> event_config %type <term> event_term @@ -53,44 +55,125 @@ do { \ %type <head> event_legacy_numeric %type <head> event_legacy_raw %type <head> event_def +%type <head> event_mod +%type <head> event_name +%type <head> event +%type <head> events +%type <head> group_def +%type <head> group +%type <head> groups %union { char *str; - unsigned long num; + u64 num; struct list_head *head; struct parse_events__term *term; } %% start: -PE_START_EVENTS events +PE_START_EVENTS start_events | -PE_START_TERMS terms +PE_START_TERMS start_terms + +start_events: groups +{ + struct parse_events_data__events *data = _data; + + parse_events_update_lists($1, &data->list); +} + +groups: +groups ',' group +{ + struct list_head *list = $1; + struct list_head *group = $3; + + parse_events_update_lists(group, list); + $$ = list; +} +| +groups ',' event +{ + struct list_head *list = $1; + struct list_head *event = $3; + + parse_events_update_lists(event, list); + $$ = list; +} +| +group +| +event + +group: +group_def ':' PE_MODIFIER_EVENT +{ + struct list_head *list = $1; + + ABORT_ON(parse_events__modifier_group(list, $3)); + $$ = list; +} +| +group_def + +group_def: +PE_NAME '{' events '}' +{ + struct list_head *list = $3; + + parse_events__set_leader($1, list); + $$ = list; +} +| +'{' events '}' +{ + struct list_head *list = $2; + + parse_events__set_leader(NULL, list); + $$ = list; +} events: -events ',' event | event +events ',' event +{ + struct list_head *event = $3; + struct list_head *list = $1; -event: -event_def PE_MODIFIER_EVENT + parse_events_update_lists(event, list); + $$ = list; +} +| +event + +event: event_mod + +event_mod: +event_name PE_MODIFIER_EVENT { - struct parse_events_data__events *data = _data; + struct list_head *list = $1; /* * Apply modifier on all events added by single event definition * (there could be more events added for multiple tracepoint * definitions via '*?'. */ - ABORT_ON(parse_events_modifier($1, $2)); - parse_events_update_lists($1, &data->list); + ABORT_ON(parse_events__modifier_event(list, $2, false)); + $$ = list; } | -event_def -{ - struct parse_events_data__events *data = _data; +event_name - parse_events_update_lists($1, &data->list); +event_name: +PE_EVENT_NAME event_def +{ + ABORT_ON(parse_events_name($2, $1)); + free($1); + $$ = $2; } +| +event_def event_def: event_pmu | event_legacy_symbol | @@ -207,7 +290,7 @@ PE_VALUE ':' PE_VALUE struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL)); $$ = list; } @@ -222,7 +305,7 @@ PE_RAW $$ = list; } -terms: event_config +start_terms: event_config { struct parse_events_data__terms *data = _data; data->terms = $1; @@ -282,7 +365,7 @@ PE_TERM '=' PE_NAME { struct parse_events__term *term; - ABORT_ON(parse_events__term_str(&term, $1, NULL, $3)); + ABORT_ON(parse_events__term_str(&term, (int)$1, NULL, $3)); $$ = term; } | @@ -290,7 +373,7 @@ PE_TERM '=' PE_VALUE { struct parse_events__term *term; - ABORT_ON(parse_events__term_num(&term, $1, NULL, $3)); + ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, $3)); $$ = term; } | @@ -298,7 +381,7 @@ PE_TERM { struct parse_events__term *term; - ABORT_ON(parse_events__term_num(&term, $1, NULL, 1)); + ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, 1)); $$ = term; } @@ -308,7 +391,7 @@ sep_slash_dc: '/' | ':' | %% -void parse_events_error(void *data __used, void *scanner __used, - char const *msg __used) +void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused, + char const *msg __maybe_unused) { } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 594f8fad5ecd..443fc116512b 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -557,7 +557,8 @@ int parse_options_usage(const char * const *usagestr, } -int parse_opt_verbosity_cb(const struct option *opt, const char *arg __used, +int parse_opt_verbosity_cb(const struct option *opt, + const char *arg __maybe_unused, int unset) { int *target = opt->value; diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h new file mode 100644 index 000000000000..316dbe7f86ed --- /dev/null +++ b/tools/perf/util/perf_regs.h @@ -0,0 +1,14 @@ +#ifndef __PERF_REGS_H +#define __PERF_REGS_H + +#ifndef NO_PERF_REGS +#include <perf_regs.h> +#else +#define PERF_REGS_MASK 0 + +static inline const char *perf_reg_name(int id __maybe_unused) +{ + return NULL; +} +#endif /* NO_PERF_REGS */ +#endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 67715a42cd6d..8a2229da594f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -9,6 +9,9 @@ #include "util.h" #include "pmu.h" #include "parse-events.h" +#include "cpumap.h" + +#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" int perf_pmu_parse(struct list_head *list, char *name); extern FILE *perf_pmu_in; @@ -69,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format) return -1; snprintf(path, PATH_MAX, - "%s/bus/event_source/devices/%s/format", sysfs, name); + "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name); if (stat(path, &st) < 0) return 0; /* no error if format does not exist */ @@ -206,7 +209,7 @@ static int pmu_type(char *name, __u32 *type) return -1; snprintf(path, PATH_MAX, - "%s/bus/event_source/devices/%s/type", sysfs, name); + "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name); if (stat(path, &st) < 0) return -1; @@ -222,6 +225,62 @@ static int pmu_type(char *name, __u32 *type) return ret; } +/* Add all pmus in sysfs to pmu list: */ +static void pmu_read_sysfs(void) +{ + char path[PATH_MAX]; + const char *sysfs; + DIR *dir; + struct dirent *dent; + + sysfs = sysfs_find_mountpoint(); + if (!sysfs) + return; + + snprintf(path, PATH_MAX, + "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + + dir = opendir(path); + if (!dir) + return; + + while ((dent = readdir(dir))) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + /* add to static LIST_HEAD(pmus): */ + perf_pmu__find(dent->d_name); + } + + closedir(dir); +} + +static struct cpu_map *pmu_cpumask(char *name) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + FILE *file; + struct cpu_map *cpus; + + sysfs = sysfs_find_mountpoint(); + if (!sysfs) + return NULL; + + snprintf(path, PATH_MAX, + "%s/bus/event_source/devices/%s/cpumask", sysfs, name); + + if (stat(path, &st) < 0) + return NULL; + + file = fopen(path, "r"); + if (!file) + return NULL; + + cpus = cpu_map__read(file); + fclose(file); + return cpus; +} + static struct perf_pmu *pmu_lookup(char *name) { struct perf_pmu *pmu; @@ -244,6 +303,8 @@ static struct perf_pmu *pmu_lookup(char *name) if (!pmu) return NULL; + pmu->cpus = pmu_cpumask(name); + pmu_aliases(name, &aliases); INIT_LIST_HEAD(&pmu->format); @@ -267,6 +328,21 @@ static struct perf_pmu *pmu_find(char *name) return NULL; } +struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) +{ + /* + * pmu iterator: If pmu is NULL, we start at the begin, + * otherwise return the next pmu. Returns NULL on end. + */ + if (!pmu) { + pmu_read_sysfs(); + pmu = list_prepare_entry(pmu, &pmus, list); + } + list_for_each_entry_continue(pmu, &pmus, list) + return pmu; + return NULL; +} + struct perf_pmu *perf_pmu__find(char *name) { struct perf_pmu *pmu; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 535f2c5258ab..53c7794fc4be 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -28,6 +28,7 @@ struct perf_pmu__alias { struct perf_pmu { char *name; __u32 type; + struct cpu_map *cpus; struct list_head format; struct list_head aliases; struct list_head list; @@ -46,5 +47,7 @@ int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits); void perf_pmu__set_format(unsigned long *bits, long from, long to); +struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); + int perf_pmu__test(void); #endif /* __PMU_H */ diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index 20ea77e93169..ec898047ebb9 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -86,8 +86,8 @@ PP_VALUE %% -void perf_pmu_error(struct list_head *list __used, - char *name __used, - char const *msg __used) +void perf_pmu_error(struct list_head *list __maybe_unused, + char *name __maybe_unused, + char const *msg __maybe_unused) { } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 0dda25d82d06..49a256e6e0a2 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -41,7 +41,7 @@ #include "symbol.h" #include "thread.h" #include "debugfs.h" -#include "trace-event.h" /* For __unused */ +#include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" #include "session.h" @@ -647,8 +647,8 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, } static int try_to_find_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs __unused, - int max_tevs __unused, const char *target) + struct probe_trace_event **tevs __maybe_unused, + int max_tevs __maybe_unused, const char *target) { if (perf_probe_event_need_dwarf(pev)) { pr_warning("Debuginfo-analysis is not supported.\n"); @@ -661,17 +661,18 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, return 0; } -int show_line_range(struct line_range *lr __unused, const char *module __unused) +int show_line_range(struct line_range *lr __maybe_unused, + const char *module __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; } -int show_available_vars(struct perf_probe_event *pevs __unused, - int npevs __unused, int max_vls __unused, - const char *module __unused, - struct strfilter *filter __unused, - bool externs __unused) +int show_available_vars(struct perf_probe_event *pevs __maybe_unused, + int npevs __maybe_unused, int max_vls __maybe_unused, + const char *module __maybe_unused, + struct strfilter *filter __maybe_unused, + bool externs __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; @@ -1099,6 +1100,7 @@ static int parse_probe_trace_command(const char *cmd, struct probe_trace_point *tp = &tev->point; char pr; char *p; + char *argv0_str = NULL, *fmt, *fmt1_str, *fmt2_str, *fmt3_str; int ret, i, argc; char **argv; @@ -1115,14 +1117,27 @@ static int parse_probe_trace_command(const char *cmd, } /* Scan event and group name. */ - ret = sscanf(argv[0], "%c:%a[^/ \t]/%a[^ \t]", - &pr, (float *)(void *)&tev->group, - (float *)(void *)&tev->event); - if (ret != 3) { + argv0_str = strdup(argv[0]); + if (argv0_str == NULL) { + ret = -ENOMEM; + goto out; + } + fmt1_str = strtok_r(argv0_str, ":", &fmt); + fmt2_str = strtok_r(NULL, "/", &fmt); + fmt3_str = strtok_r(NULL, " \t", &fmt); + if (fmt1_str == NULL || strlen(fmt1_str) != 1 || fmt2_str == NULL + || fmt3_str == NULL) { semantic_error("Failed to parse event name: %s\n", argv[0]); ret = -EINVAL; goto out; } + pr = fmt1_str[0]; + tev->group = strdup(fmt2_str); + tev->event = strdup(fmt3_str); + if (tev->group == NULL || tev->event == NULL) { + ret = -ENOMEM; + goto out; + } pr_debug("Group:%s Event:%s probe:%c\n", tev->group, tev->event, pr); tp->retprobe = (pr == 'r'); @@ -1134,10 +1149,17 @@ static int parse_probe_trace_command(const char *cmd, p++; } else p = argv[1]; - ret = sscanf(p, "%a[^+]+%lu", (float *)(void *)&tp->symbol, - &tp->offset); - if (ret == 1) + fmt1_str = strtok_r(p, "+", &fmt); + tp->symbol = strdup(fmt1_str); + if (tp->symbol == NULL) { + ret = -ENOMEM; + goto out; + } + fmt2_str = strtok_r(NULL, "", &fmt); + if (fmt2_str == NULL) tp->offset = 0; + else + tp->offset = strtoul(fmt2_str, NULL, 10); tev->nargs = argc - 2; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); @@ -1161,6 +1183,7 @@ static int parse_probe_trace_command(const char *cmd, } ret = 0; out: + free(argv0_str); argv_free(argv); return ret; } @@ -2183,7 +2206,7 @@ static struct strfilter *available_func_filter; * If a symbol corresponds to a function with global binding and * matches filter return 0. For all others return 1. */ -static int filter_available_functions(struct map *map __unused, +static int filter_available_functions(struct map *map __maybe_unused, struct symbol *sym) { if (sym->binding == STB_GLOBAL && @@ -2307,10 +2330,17 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec) function = NULL; } if (!pev->group) { - char *ptr1, *ptr2; + char *ptr1, *ptr2, *exec_copy; pev->group = zalloc(sizeof(char *) * 64); - ptr1 = strdup(basename(exec)); + exec_copy = strdup(exec); + if (!exec_copy) { + ret = -ENOMEM; + pr_warning("Failed to copy exec string.\n"); + goto out; + } + + ptr1 = strdup(basename(exec_copy)); if (ptr1) { ptr2 = strpbrk(ptr1, "-._"); if (ptr2) @@ -2319,6 +2349,7 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec) ptr1); free(ptr1); } + free(exec_copy); } free(pp->function); pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index d448984ed789..1daf5c14e751 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -207,7 +207,7 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, #else /* With older elfutils, this just support kernel module... */ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, - Dwarf_Addr addr __used) + Dwarf_Addr addr __maybe_unused) { const char *path = kernel_get_module_path("kernel"); @@ -525,8 +525,10 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, return -ENOENT; } /* Verify it is a data structure */ - if (dwarf_tag(&type) != DW_TAG_structure_type) { - pr_warning("%s is not a data structure.\n", varname); + tag = dwarf_tag(&type); + if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { + pr_warning("%s is not a data structure nor an union.\n", + varname); return -EINVAL; } @@ -539,8 +541,9 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, *ref_ptr = ref; } else { /* Verify it is a data structure */ - if (tag != DW_TAG_structure_type) { - pr_warning("%s is not a data structure.\n", varname); + if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { + pr_warning("%s is not a data structure nor an union.\n", + varname); return -EINVAL; } if (field->name[0] == '[') { @@ -567,10 +570,15 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } /* Get the offset of the field */ - ret = die_get_data_member_location(die_mem, &offs); - if (ret < 0) { - pr_warning("Failed to get the offset of %s.\n", field->name); - return ret; + if (tag == DW_TAG_union_type) { + offs = 0; + } else { + ret = die_get_data_member_location(die_mem, &offs); + if (ret < 0) { + pr_warning("Failed to get the offset of %s.\n", + field->name); + return ret; + } } ref->offset += (long)offs; @@ -1419,7 +1427,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, } static int line_range_walk_cb(const char *fname, int lineno, - Dwarf_Addr addr __used, + Dwarf_Addr addr __maybe_unused, void *data) { struct line_finder *lf = data; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 0688bfb6d280..9181bf212fb9 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -627,7 +627,7 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, * This will group just the fds for this single evsel, to group * multiple events, use evlist.open(). */ - if (perf_evsel__open(evsel, cpus, threads, group, NULL) < 0) { + if (perf_evsel__open(evsel, cpus, threads) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -672,7 +672,7 @@ struct pyrf_evlist { }; static int pyrf_evlist__init(struct pyrf_evlist *pevlist, - PyObject *args, PyObject *kwargs __used) + PyObject *args, PyObject *kwargs __maybe_unused) { PyObject *pcpus = NULL, *pthreads = NULL; struct cpu_map *cpus; @@ -733,7 +733,8 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, } static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, - PyObject *args __used, PyObject *kwargs __used) + PyObject *args __maybe_unused, + PyObject *kwargs __maybe_unused) { struct perf_evlist *evlist = &pevlist->evlist; PyObject *list = PyList_New(0); @@ -765,7 +766,8 @@ free_list: static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, - PyObject *args, PyObject *kwargs __used) + PyObject *args, + PyObject *kwargs __maybe_unused) { struct perf_evlist *evlist = &pevlist->evlist; PyObject *pevsel; @@ -803,7 +805,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (pyevent == NULL) return PyErr_NoMemory(); - err = perf_evlist__parse_sample(evlist, event, &pevent->sample, false); + err = perf_evlist__parse_sample(evlist, event, &pevent->sample); if (err) return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); @@ -824,7 +826,10 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group)) return NULL; - if (perf_evlist__open(evlist, group) < 0) { + if (group) + perf_evlist__set_leader(evlist); + + if (perf_evlist__open(evlist) < 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 02dfa19a467f..f80605eb1855 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -25,16 +25,16 @@ #include <ctype.h> #include <errno.h> -#include "../../perf.h" #include "../util.h" +#include <EXTERN.h> +#include <perl.h> + +#include "../../perf.h" #include "../thread.h" #include "../event.h" #include "../trace-event.h" #include "../evsel.h" -#include <EXTERN.h> -#include <perl.h> - void boot_Perf__Trace__Context(pTHX_ CV *cv); void boot_DynaLoader(pTHX_ CV *cv); typedef PerlInterpreter * INTERP; @@ -237,16 +237,16 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline -struct event_format *find_cache_event(struct pevent *pevent, int type) +static inline struct event_format *find_cache_event(struct perf_evsel *evsel) { static char ev_name[256]; struct event_format *event; + int type = evsel->attr.config; if (events[type]) return events[type]; - events[type] = event = pevent_find_event(pevent, type); + events[type] = event = evsel->tp_format; if (!event) return NULL; @@ -257,23 +257,22 @@ struct event_format *find_cache_event(struct pevent *pevent, int type) return event; } -static void perl_process_tracepoint(union perf_event *perf_event __unused, - struct pevent *pevent, +static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, struct perf_sample *sample, struct perf_evsel *evsel, - struct machine *machine __unused, - struct thread *thread) + struct machine *machine __maybe_unused, + struct addr_location *al) { struct format_field *field; static char handler[256]; unsigned long long val; unsigned long s, ns; struct event_format *event; - int type; int pid; int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; + struct thread *thread = al->thread; char *comm = thread->comm; dSP; @@ -281,13 +280,11 @@ static void perl_process_tracepoint(union perf_event *perf_event __unused, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - type = trace_parse_common_type(pevent, data); - - event = find_cache_event(pevent, type); + event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %d", type); + die("ug! no event found for type %" PRIu64, evsel->attr.config); - pid = trace_parse_common_pid(pevent, data); + pid = raw_field_value(event, "common_pid", data); sprintf(handler, "%s::%s", event->system, event->name); @@ -320,7 +317,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __unused, offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); } else { /* FIELD_IS_NUMERIC */ - val = read_size(pevent, data + field->offset, + val = read_size(event, data + field->offset, field->size); if (field->flags & FIELD_IS_SIGNED) { XPUSHs(sv_2mortal(newSViv(val))); @@ -349,11 +346,11 @@ static void perl_process_tracepoint(union perf_event *perf_event __unused, LEAVE; } -static void perl_process_event_generic(union perf_event *pevent __unused, +static void perl_process_event_generic(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __unused, - struct machine *machine __unused, - struct thread *thread __unused) + struct perf_evsel *evsel, + struct machine *machine __maybe_unused, + struct addr_location *al __maybe_unused) { dSP; @@ -363,7 +360,7 @@ static void perl_process_event_generic(union perf_event *pevent __unused, ENTER; SAVETMPS; PUSHMARK(SP); - XPUSHs(sv_2mortal(newSVpvn((const char *)pevent, pevent->header.size))); + XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size))); XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample)))); XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size))); @@ -376,14 +373,13 @@ static void perl_process_event_generic(union perf_event *pevent __unused, } static void perl_process_event(union perf_event *event, - struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct thread *thread) + struct addr_location *al) { - perl_process_tracepoint(event, pevent, sample, evsel, machine, thread); - perl_process_event_generic(event, sample, evsel, machine, thread); + perl_process_tracepoint(event, sample, evsel, machine, al); + perl_process_event_generic(event, sample, evsel, machine, al); } static void run_start_sub(void) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index ce4d1b0c3862..730c6630cba5 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -27,10 +27,12 @@ #include <errno.h> #include "../../perf.h" +#include "../evsel.h" #include "../util.h" #include "../event.h" #include "../thread.h" #include "../trace-event.h" +#include "../evsel.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -194,16 +196,21 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline -struct event_format *find_cache_event(struct pevent *pevent, int type) +static inline struct event_format *find_cache_event(struct perf_evsel *evsel) { static char ev_name[256]; struct event_format *event; + int type = evsel->attr.config; + /* + * XXX: Do we really need to cache this since now we have evsel->tp_format + * cached already? Need to re-read this "cache" routine that as well calls + * define_event_symbols() :-\ + */ if (events[type]) return events[type]; - events[type] = event = pevent_find_event(pevent, type); + events[type] = event = evsel->tp_format; if (!event) return NULL; @@ -214,12 +221,12 @@ struct event_format *find_cache_event(struct pevent *pevent, int type) return event; } -static void python_process_event(union perf_event *perf_event __unused, - struct pevent *pevent, +static void python_process_tracepoint(union perf_event *perf_event + __maybe_unused, struct perf_sample *sample, - struct perf_evsel *evsel __unused, - struct machine *machine __unused, - struct thread *thread) + struct perf_evsel *evsel, + struct machine *machine __maybe_unused, + struct addr_location *al) { PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; static char handler_name[256]; @@ -228,24 +235,22 @@ static void python_process_event(union perf_event *perf_event __unused, unsigned long s, ns; struct event_format *event; unsigned n = 0; - int type; int pid; int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; + struct thread *thread = al->thread; char *comm = thread->comm; t = PyTuple_New(MAX_FIELDS); if (!t) Py_FatalError("couldn't create Python tuple"); - type = trace_parse_common_type(pevent, data); - - event = find_cache_event(pevent, type); + event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %d", type); + die("ug! no event found for type %d", (int)evsel->attr.config); - pid = trace_parse_common_pid(pevent, data); + pid = raw_field_value(event, "common_pid", data); sprintf(handler_name, "%s__%s", event->system, event->name); @@ -290,7 +295,7 @@ static void python_process_event(union perf_event *perf_event __unused, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(pevent, data + field->offset, + val = read_size(event, data + field->offset, field->size); if (field->flags & FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && @@ -335,6 +340,84 @@ static void python_process_event(union perf_event *perf_event __unused, Py_DECREF(t); } +static void python_process_general_event(union perf_event *perf_event + __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __maybe_unused, + struct addr_location *al) +{ + PyObject *handler, *retval, *t, *dict; + static char handler_name[64]; + unsigned n = 0; + struct thread *thread = al->thread; + + /* + * Use the MAX_FIELDS to make the function expandable, though + * currently there is only one item for the tuple. + */ + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + dict = PyDict_New(); + if (!dict) + Py_FatalError("couldn't create Python dictionary"); + + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); + + handler = PyDict_GetItemString(main_dict, handler_name); + if (!handler || !PyCallable_Check(handler)) + goto exit; + + PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + (const char *)&evsel->attr, sizeof(evsel->attr))); + PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + (const char *)sample, sizeof(*sample))); + PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + (const char *)sample->raw_data, sample->raw_size)); + PyDict_SetItemString(dict, "comm", + PyString_FromString(thread->comm)); + if (al->map) { + PyDict_SetItemString(dict, "dso", + PyString_FromString(al->map->dso->name)); + } + if (al->sym) { + PyDict_SetItemString(dict, "symbol", + PyString_FromString(al->sym->name)); + } + + PyTuple_SetItem(t, n++, dict); + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + retval = PyObject_CallObject(handler, t); + if (retval == NULL) + handler_call_die(handler_name); +exit: + Py_DECREF(dict); + Py_DECREF(t); +} + +static void python_process_event(union perf_event *perf_event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine, + struct addr_location *al) +{ + switch (evsel->attr.type) { + case PERF_TYPE_TRACEPOINT: + python_process_tracepoint(perf_event, sample, evsel, + machine, al); + break; + /* Reserve for future process_hw/sw/raw APIs */ + default: + python_process_general_event(perf_event, sample, evsel, + machine, al); + } +} + static int run_start_sub(void) { PyObject *handler, *retval; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 2437fb0b463a..8cdd23239c90 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -15,6 +15,9 @@ #include "util.h" #include "cpumap.h" #include "event-parse.h" +#include "perf_regs.h" +#include "unwind.h" +#include "vdso.h" static int perf_session__open(struct perf_session *self, bool force) { @@ -209,6 +212,7 @@ void perf_session__delete(struct perf_session *self) machine__exit(&self->host_machine); close(self->fd); free(self); + vdso__exit(); } void machine__remove_thread(struct machine *self, struct thread *th) @@ -288,10 +292,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self, return bi; } -int machine__resolve_callchain(struct machine *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) +static int machine__resolve_callchain_sample(struct machine *machine, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) + { u8 cpumode = PERF_RECORD_MISC_USER; unsigned int i; @@ -316,11 +321,14 @@ int machine__resolve_callchain(struct machine *self, if (ip >= PERF_CONTEXT_MAX) { switch (ip) { case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; break; + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; break; + cpumode = PERF_RECORD_MISC_KERNEL; + break; case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; break; + cpumode = PERF_RECORD_MISC_USER; + break; default: pr_debug("invalid callchain context: " "%"PRId64"\n", (s64) ip); @@ -335,7 +343,7 @@ int machine__resolve_callchain(struct machine *self, } al.filtered = false; - thread__find_addr_location(thread, self, cpumode, + thread__find_addr_location(thread, machine, cpumode, MAP__FUNCTION, ip, &al, NULL); if (al.sym != NULL) { if (sort__has_parent && !*parent && @@ -354,49 +362,92 @@ int machine__resolve_callchain(struct machine *self, return 0; } -static int process_event_synth_tracing_data_stub(union perf_event *event __used, - struct perf_session *session __used) +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + struct callchain_cursor *cursor = arg; + return callchain_cursor_append(cursor, entry->ip, + entry->map, entry->sym); +} + +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent) + +{ + int ret; + + callchain_cursor_reset(&callchain_cursor); + + ret = machine__resolve_callchain_sample(machine, thread, + sample->callchain, parent); + if (ret) + return ret; + + /* Can we do dwarf post unwind? */ + if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + return 0; + + /* Bail out if nothing was captured. */ + if ((!sample->user_regs.regs) || + (!sample->user_stack.size)) + return 0; + + return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + thread, evsel->attr.sample_regs_user, + sample); + +} + +static int process_event_synth_tracing_data_stub(union perf_event *event + __maybe_unused, + struct perf_session *session + __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_synth_attr_stub(union perf_event *event __used, - struct perf_evlist **pevlist __used) +static int process_event_synth_attr_stub(union perf_event *event __maybe_unused, + struct perf_evlist **pevlist + __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_sample_stub(struct perf_tool *tool __used, - union perf_event *event __used, - struct perf_sample *sample __used, - struct perf_evsel *evsel __used, - struct machine *machine __used) +static int process_event_sample_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_stub(struct perf_tool *tool __used, - union perf_event *event __used, - struct perf_sample *sample __used, - struct machine *machine __used) +static int process_event_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round_stub(struct perf_tool *tool __used, - union perf_event *event __used, - struct perf_session *perf_session __used) +static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_type_stub(struct perf_tool *tool __used, - union perf_event *event __used) +static int process_event_type_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -473,7 +524,7 @@ static void swap_sample_id_all(union perf_event *event, void *data) } static void perf_event__all64_swap(union perf_event *event, - bool sample_id_all __used) + bool sample_id_all __maybe_unused) { struct perf_event_header *hdr = &event->header; mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr)); @@ -487,7 +538,7 @@ static void perf_event__comm_swap(union perf_event *event, bool sample_id_all) if (sample_id_all) { void *data = &event->comm.comm; - data += ALIGN(strlen(data) + 1, sizeof(u64)); + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); swap_sample_id_all(event, data); } } @@ -504,7 +555,7 @@ static void perf_event__mmap_swap(union perf_event *event, if (sample_id_all) { void *data = &event->mmap.filename; - data += ALIGN(strlen(data) + 1, sizeof(u64)); + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); swap_sample_id_all(event, data); } } @@ -584,7 +635,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr) } static void perf_event__hdr_attr_swap(union perf_event *event, - bool sample_id_all __used) + bool sample_id_all __maybe_unused) { size_t size; @@ -596,14 +647,14 @@ static void perf_event__hdr_attr_swap(union perf_event *event, } static void perf_event__event_type_swap(union perf_event *event, - bool sample_id_all __used) + bool sample_id_all __maybe_unused) { event->event_type.event_type.event_id = bswap_64(event->event_type.event_type.event_id); } static void perf_event__tracing_data_swap(union perf_event *event, - bool sample_id_all __used) + bool sample_id_all __maybe_unused) { event->tracing_data.size = bswap_32(event->tracing_data.size); } @@ -652,7 +703,7 @@ static int perf_session_deliver_event(struct perf_session *session, struct perf_tool *tool, u64 file_offset); -static void flush_sample_queue(struct perf_session *s, +static int flush_sample_queue(struct perf_session *s, struct perf_tool *tool) { struct ordered_samples *os = &s->ordered_samples; @@ -665,19 +716,21 @@ static void flush_sample_queue(struct perf_session *s, int ret; if (!tool->ordered_samples || !limit) - return; + return 0; list_for_each_entry_safe(iter, tmp, head, list) { if (iter->timestamp > limit) break; - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample, - s->header.needs_swap); + ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); if (ret) pr_err("Can't parse sample, err = %d\n", ret); - else - perf_session_deliver_event(s, iter->event, &sample, tool, - iter->file_offset); + else { + ret = perf_session_deliver_event(s, iter->event, &sample, tool, + iter->file_offset); + if (ret) + return ret; + } os->last_flush = iter->timestamp; list_del(&iter->list); @@ -697,6 +750,8 @@ static void flush_sample_queue(struct perf_session *s, } os->nr_samples = 0; + + return 0; } /* @@ -739,13 +794,14 @@ static void flush_sample_queue(struct perf_session *s, * etc... */ static int process_finished_round(struct perf_tool *tool, - union perf_event *event __used, + union perf_event *event __maybe_unused, struct perf_session *session) { - flush_sample_queue(session, tool); - session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; + int ret = flush_sample_queue(session, tool); + if (!ret) + session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; - return 0; + return ret; } /* The queue is ordered by time */ @@ -860,6 +916,34 @@ static void branch_stack__printf(struct perf_sample *sample) sample->branch_stack->entries[i].to); } +static void regs_dump__printf(u64 mask, u64 *regs) +{ + unsigned rid, i = 0; + + for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) { + u64 val = regs[i++]; + + printf(".... %-5s 0x%" PRIx64 "\n", + perf_reg_name(rid), val); + } +} + +static void regs_user__printf(struct perf_sample *sample, u64 mask) +{ + struct regs_dump *user_regs = &sample->user_regs; + + if (user_regs->regs) { + printf("... user regs: mask 0x%" PRIx64 "\n", mask); + regs_dump__printf(mask, user_regs->regs); + } +} + +static void stack_user__printf(struct stack_dump *dump) +{ + printf("... ustack: size %" PRIu64 ", offset 0x%x\n", + dump->size, dump->offset); +} + static void perf_session__print_tstamp(struct perf_session *session, union perf_event *event, struct perf_sample *sample) @@ -897,7 +981,7 @@ static void dump_event(struct perf_session *session, union perf_event *event, event->header.size, perf_event__name(event->header.type)); } -static void dump_sample(struct perf_session *session, union perf_event *event, +static void dump_sample(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample) { u64 sample_type; @@ -909,13 +993,19 @@ static void dump_sample(struct perf_session *session, union perf_event *event, event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); - sample_type = perf_evlist__sample_type(session->evlist); + sample_type = evsel->attr.sample_type; if (sample_type & PERF_SAMPLE_CALLCHAIN) callchain__printf(sample); if (sample_type & PERF_SAMPLE_BRANCH_STACK) branch_stack__printf(sample); + + if (sample_type & PERF_SAMPLE_REGS_USER) + regs_user__printf(sample, evsel->attr.sample_regs_user); + + if (sample_type & PERF_SAMPLE_STACK_USER) + stack_user__printf(&sample->user_stack); } static struct machine * @@ -973,7 +1063,7 @@ static int perf_session_deliver_event(struct perf_session *session, switch (event->header.type) { case PERF_RECORD_SAMPLE: - dump_sample(session, event, sample); + dump_sample(evsel, event, sample); if (evsel == NULL) { ++session->hists.stats.nr_unknown_id; return 0; @@ -1083,8 +1173,7 @@ static int perf_session__process_event(struct perf_session *session, /* * For all kernel events we get the sample data */ - ret = perf_evlist__parse_sample(session->evlist, event, &sample, - session->header.needs_swap); + ret = perf_evlist__parse_sample(session->evlist, event, &sample); if (ret) return ret; @@ -1369,7 +1458,7 @@ more: err = 0; /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; - flush_sample_queue(session, tool); + err = flush_sample_queue(session, tool); out_err: perf_session__warn_about_errors(session, tool); perf_session_free_sample_buffers(session); @@ -1498,9 +1587,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, return NULL; } -void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, int print_sym, - int print_dso, int print_symoffset) +void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, + struct perf_sample *sample, struct machine *machine, + int print_sym, int print_dso, int print_symoffset) { struct addr_location al; struct callchain_cursor_node *node; @@ -1514,8 +1603,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, if (symbol_conf.use_callchain && sample->callchain) { - if (machine__resolve_callchain(machine, al.thread, - sample->callchain, NULL) != 0) { + + if (machine__resolve_callchain(machine, evsel, al.thread, + sample, NULL) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 1f7ec87db7d7..aab414fbb64b 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -36,9 +36,7 @@ struct perf_session { struct pevent *pevent; /* * FIXME: Need to split this up further, we need global - * stats + per event stats. 'perf diff' also needs - * to properly support multiple events in a single - * perf.data file. + * stats + per event stats. */ struct hists hists; int fd; @@ -129,9 +127,9 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); -void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, int print_sym, - int print_dso, int print_symoffset); +void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, + struct perf_sample *sample, struct machine *machine, + int print_sym, int print_dso, int print_symoffset); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 0f5a0a496bc4..b5b1b9211960 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -8,12 +8,11 @@ const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; int sort__need_collapse = 0; int sort__has_parent = 0; +int sort__has_sym = 0; int sort__branch_mode = -1; /* -1 = means not set */ enum sort_type sort__first_dimension; -char * field_sep; - LIST_HEAD(hist_entry__sort_list); static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) @@ -23,11 +22,11 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) va_start(ap, fmt); n = vsnprintf(bf, size, fmt, ap); - if (field_sep && n > 0) { + if (symbol_conf.field_sep && n > 0) { char *sep = bf; while (1) { - sep = strchr(sep, *field_sep); + sep = strchr(sep, *symbol_conf.field_sep); if (sep == NULL) break; *sep = '.'; @@ -172,7 +171,7 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, u64 ip, char level, char *bf, size_t size, - unsigned int width __used) + unsigned int width __maybe_unused) { size_t ret = 0; @@ -207,7 +206,8 @@ struct sort_entry sort_dso = { }; static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) + size_t size, + unsigned int width __maybe_unused) { return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, self->level, bf, size, width); @@ -250,7 +250,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) } static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) + size_t size, + unsigned int width __maybe_unused) { FILE *fp; char cmd[PATH_MAX + 2], *path = self->srcline, *nl; @@ -399,7 +400,8 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) } static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) + size_t size, + unsigned int width __maybe_unused) { struct addr_map_symbol *from = &self->branch_info->from; return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, @@ -408,7 +410,8 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, } static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width __used) + size_t size, + unsigned int width __maybe_unused) { struct addr_map_symbol *to = &self->branch_info->to; return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, @@ -509,6 +512,10 @@ int sort_dimension__add(const char *tok) return -EINVAL; } sort__has_parent = 1; + } else if (sd->entry == &sort_sym || + sd->entry == &sort_sym_from || + sd->entry == &sort_sym_to) { + sort__has_sym = 1; } if (sd->taken) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index e724b26acd51..12d634792de5 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -31,8 +31,8 @@ extern const char *parent_pattern; extern const char default_sort_order[]; extern int sort__need_collapse; extern int sort__has_parent; +extern int sort__has_sym; extern int sort__branch_mode; -extern char *field_sep; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c new file mode 100644 index 000000000000..23742126f47c --- /dev/null +++ b/tools/perf/util/stat.c @@ -0,0 +1,57 @@ +#include <math.h> + +#include "stat.h" + +void update_stats(struct stats *stats, u64 val) +{ + double delta; + + stats->n++; + delta = val - stats->mean; + stats->mean += delta / stats->n; + stats->M2 += delta*(val - stats->mean); +} + +double avg_stats(struct stats *stats) +{ + return stats->mean; +} + +/* + * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance + * + * (\Sum n_i^2) - ((\Sum n_i)^2)/n + * s^2 = ------------------------------- + * n - 1 + * + * http://en.wikipedia.org/wiki/Stddev + * + * The std dev of the mean is related to the std dev by: + * + * s + * s_mean = ------- + * sqrt(n) + * + */ +double stddev_stats(struct stats *stats) +{ + double variance, variance_mean; + + if (!stats->n) + return 0.0; + + variance = stats->M2 / (stats->n - 1); + variance_mean = variance / stats->n; + + return sqrt(variance_mean); +} + +double rel_stddev_stats(double stddev, double avg) +{ + double pct = 0.0; + + if (avg) + pct = 100.0 * stddev/avg; + + return pct; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h new file mode 100644 index 000000000000..588367c3c767 --- /dev/null +++ b/tools/perf/util/stat.h @@ -0,0 +1,16 @@ +#ifndef __PERF_STATS_H +#define __PERF_STATS_H + +#include "types.h" + +struct stats +{ + double n, mean, M2; +}; + +void update_stats(struct stats *stats, u64 val); +double avg_stats(struct stats *stats); +double stddev_stats(struct stats *stats); +double rel_stddev_stats(double stddev, double avg); + +#endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 199bc4d8905d..32170590892d 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,5 +1,5 @@ #include "util.h" -#include "string.h" +#include "linux/string.h" #define K 1024LL /* @@ -335,3 +335,19 @@ char *rtrim(char *s) return s; } + +/** + * memdup - duplicate region of memory + * @src: memory region to duplicate + * @len: memory region length + */ +void *memdup(const void *src, size_t len) +{ + void *p; + + p = malloc(len); + if (p) + memcpy(p, src, len); + + return p; +} diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 95856ff3dda4..155d8b7078a7 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -93,7 +93,7 @@ out: void strlist__remove(struct strlist *slist, struct str_node *snode) { - str_node__delete(snode, slist->dupstr); + rblist__remove_node(&slist->rblist, &snode->rb_node); } struct str_node *strlist__find(struct strlist *slist, const char *entry) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c new file mode 100644 index 000000000000..db0cc92cf2ea --- /dev/null +++ b/tools/perf/util/symbol-elf.c @@ -0,0 +1,841 @@ +#include <libelf.h> +#include <gelf.h> +#include <elf.h> +#include <fcntl.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <unistd.h> +#include <inttypes.h> + +#include "symbol.h" +#include "debug.h" + +#ifndef NT_GNU_BUILD_ID +#define NT_GNU_BUILD_ID 3 +#endif + +/** + * elf_symtab__for_each_symbol - iterate thru all the symbols + * + * @syms: struct elf_symtab instance to iterate + * @idx: uint32_t idx + * @sym: GElf_Sym iterator + */ +#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \ + for (idx = 0, gelf_getsym(syms, idx, &sym);\ + idx < nr_syms; \ + idx++, gelf_getsym(syms, idx, &sym)) + +static inline uint8_t elf_sym__type(const GElf_Sym *sym) +{ + return GELF_ST_TYPE(sym->st_info); +} + +static inline int elf_sym__is_function(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_FUNC && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF; +} + +static inline bool elf_sym__is_object(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_OBJECT && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF; +} + +static inline int elf_sym__is_label(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_NOTYPE && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF && + sym->st_shndx != SHN_ABS; +} + +static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sym__is_function(sym); + case MAP__VARIABLE: + return elf_sym__is_object(sym); + default: + return false; + } +} + +static inline const char *elf_sym__name(const GElf_Sym *sym, + const Elf_Data *symstrs) +{ + return symstrs->d_buf + sym->st_name; +} + +static inline const char *elf_sec__name(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return secstrs->d_buf + shdr->sh_name; +} + +static inline int elf_sec__is_text(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; +} + +static inline bool elf_sec__is_data(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; +} + +static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs, + enum map_type type) +{ + switch (type) { + case MAP__FUNCTION: + return elf_sec__is_text(shdr, secstrs); + case MAP__VARIABLE: + return elf_sec__is_data(shdr, secstrs); + default: + return false; + } +} + +static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) +{ + Elf_Scn *sec = NULL; + GElf_Shdr shdr; + size_t cnt = 1; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + gelf_getshdr(sec, &shdr); + + if ((addr >= shdr.sh_addr) && + (addr < (shdr.sh_addr + shdr.sh_size))) + return cnt; + + ++cnt; + } + + return -1; +} + +static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name, + size_t *idx) +{ + Elf_Scn *sec = NULL; + size_t cnt = 1; + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) + return NULL; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *str; + + gelf_getshdr(sec, shp); + str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); + if (!strcmp(name, str)) { + if (idx) + *idx = cnt; + break; + } + ++cnt; + } + + return sec; +} + +#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) + +#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) + +/* + * We need to check if we have a .dynsym, so that we can handle the + * .plt, synthesizing its symbols, that aren't on the symtabs (be it + * .dynsym or .symtab). + * And always look at the original dso, not at debuginfo packages, that + * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). + */ +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map, + symbol_filter_t filter) +{ + uint32_t nr_rel_entries, idx; + GElf_Sym sym; + u64 plt_offset; + GElf_Shdr shdr_plt; + struct symbol *f; + GElf_Shdr shdr_rel_plt, shdr_dynsym; + Elf_Data *reldata, *syms, *symstrs; + Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym; + size_t dynsym_idx; + GElf_Ehdr ehdr; + char sympltname[1024]; + Elf *elf; + int nr = 0, symidx, err = 0; + + if (!ss->dynsym) + return 0; + + elf = ss->elf; + ehdr = ss->ehdr; + + scn_dynsym = ss->dynsym; + shdr_dynsym = ss->dynshdr; + dynsym_idx = ss->dynsym_idx; + + if (scn_dynsym == NULL) + goto out_elf_end; + + scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, + ".rela.plt", NULL); + if (scn_plt_rel == NULL) { + scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, + ".rel.plt", NULL); + if (scn_plt_rel == NULL) + goto out_elf_end; + } + + err = -1; + + if (shdr_rel_plt.sh_link != dynsym_idx) + goto out_elf_end; + + if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL) + goto out_elf_end; + + /* + * Fetch the relocation section to find the idxes to the GOT + * and the symbols in the .dynsym they refer to. + */ + reldata = elf_getdata(scn_plt_rel, NULL); + if (reldata == NULL) + goto out_elf_end; + + syms = elf_getdata(scn_dynsym, NULL); + if (syms == NULL) + goto out_elf_end; + + scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link); + if (scn_symstrs == NULL) + goto out_elf_end; + + symstrs = elf_getdata(scn_symstrs, NULL); + if (symstrs == NULL) + goto out_elf_end; + + if (symstrs->d_size == 0) + goto out_elf_end; + + nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; + plt_offset = shdr_plt.sh_offset; + + if (shdr_rel_plt.sh_type == SHT_RELA) { + GElf_Rela pos_mem, *pos; + + elf_section__for_each_rela(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + STB_GLOBAL, sympltname); + if (!f) + goto out_elf_end; + + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&dso->symbols[map->type], f); + ++nr; + } + } + } else if (shdr_rel_plt.sh_type == SHT_REL) { + GElf_Rel pos_mem, *pos; + elf_section__for_each_rel(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + STB_GLOBAL, sympltname); + if (!f) + goto out_elf_end; + + if (filter && filter(map, f)) + symbol__delete(f); + else { + symbols__insert(&dso->symbols[map->type], f); + ++nr; + } + } + } + + err = 0; +out_elf_end: + if (err == 0) + return nr; + pr_debug("%s: problems reading %s PLT info.\n", + __func__, dso->long_name); + return 0; +} + +/* + * Align offset to 4 bytes as needed for note name and descriptor data. + */ +#define NOTE_ALIGN(n) (((n) + 3) & -4U) + +static int elf_read_build_id(Elf *elf, void *bf, size_t size) +{ + int err = -1; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + void *ptr; + + if (size < BUILD_ID_SIZE) + goto out; + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out; + } + + /* + * Check following sections for notes: + * '.note.gnu.build-id' + * '.notes' + * '.note' (VDSO specific) + */ + do { + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note.gnu.build-id", NULL); + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".notes", NULL); + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note", NULL); + if (sec) + break; + + return err; + + } while (0); + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out; + + ptr = data->d_buf; + while (ptr < (data->d_buf + data->d_size)) { + GElf_Nhdr *nhdr = ptr; + size_t namesz = NOTE_ALIGN(nhdr->n_namesz), + descsz = NOTE_ALIGN(nhdr->n_descsz); + const char *name; + + ptr += sizeof(*nhdr); + name = ptr; + ptr += namesz; + if (nhdr->n_type == NT_GNU_BUILD_ID && + nhdr->n_namesz == sizeof("GNU")) { + if (memcmp(name, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + err = descsz; + break; + } + } + ptr += descsz; + } + +out: + return err; +} + +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + int fd, err = -1; + Elf *elf; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + err = elf_read_build_id(elf, bf, size); + + elf_end(elf); +out_close: + close(fd); +out: + return err; +} + +int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +{ + int fd, err = -1; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + while (1) { + char bf[BUFSIZ]; + GElf_Nhdr nhdr; + size_t namesz, descsz; + + if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) + break; + + namesz = NOTE_ALIGN(nhdr.n_namesz); + descsz = NOTE_ALIGN(nhdr.n_descsz); + if (nhdr.n_type == NT_GNU_BUILD_ID && + nhdr.n_namesz == sizeof("GNU")) { + if (read(fd, bf, namesz) != (ssize_t)namesz) + break; + if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(descsz, size); + if (read(fd, build_id, sz) == (ssize_t)sz) { + memset(build_id + sz, 0, size - sz); + err = 0; + break; + } + } else if (read(fd, bf, descsz) != (ssize_t)descsz) + break; + } else { + int n = namesz + descsz; + if (read(fd, bf, n) != n) + break; + } + } + close(fd); +out: + return err; +} + +int filename__read_debuglink(const char *filename, char *debuglink, + size_t size) +{ + int fd, err = -1; + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_close; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out_close; + } + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu_debuglink", NULL); + if (sec == NULL) + goto out_close; + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out_close; + + /* the start of this section is a zero-terminated string */ + strncpy(debuglink, data->d_buf, size); + + elf_end(elf); + +out_close: + close(fd); +out: + return err; +} + +static int dso__swap_init(struct dso *dso, unsigned char eidata) +{ + static unsigned int const endian = 1; + + dso->needs_swap = DSO_SWAP__NO; + + switch (eidata) { + case ELFDATA2LSB: + /* We are big endian, DSO is little endian. */ + if (*(unsigned char const *)&endian != 1) + dso->needs_swap = DSO_SWAP__YES; + break; + + case ELFDATA2MSB: + /* We are little endian, DSO is big endian. */ + if (*(unsigned char const *)&endian != 0) + dso->needs_swap = DSO_SWAP__YES; + break; + + default: + pr_err("unrecognized DSO data encoding %d\n", eidata); + return -EINVAL; + } + + return 0; +} + +bool symsrc__possibly_runtime(struct symsrc *ss) +{ + return ss->dynsym || ss->opdsec; +} + +bool symsrc__has_symtab(struct symsrc *ss) +{ + return ss->symtab != NULL; +} + +void symsrc__destroy(struct symsrc *ss) +{ + free(ss->name); + elf_end(ss->elf); + close(ss->fd); +} + +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, + enum dso_binary_type type) +{ + int err = -1; + GElf_Ehdr ehdr; + Elf *elf; + int fd; + + fd = open(name, O_RDONLY); + if (fd < 0) + return -1; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + goto out_close; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_debug("%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) + goto out_elf_end; + + /* Always reject images with a mismatched build-id: */ + if (dso->has_build_id) { + u8 build_id[BUILD_ID_SIZE]; + + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) + goto out_elf_end; + + if (!dso__build_id_equal(dso, build_id)) + goto out_elf_end; + } + + ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab", + NULL); + if (ss->symshdr.sh_type != SHT_SYMTAB) + ss->symtab = NULL; + + ss->dynsym_idx = 0; + ss->dynsym = elf_section_by_name(elf, &ehdr, &ss->dynshdr, ".dynsym", + &ss->dynsym_idx); + if (ss->dynshdr.sh_type != SHT_DYNSYM) + ss->dynsym = NULL; + + ss->opdidx = 0; + ss->opdsec = elf_section_by_name(elf, &ehdr, &ss->opdshdr, ".opd", + &ss->opdidx); + if (ss->opdshdr.sh_type != SHT_PROGBITS) + ss->opdsec = NULL; + + if (dso->kernel == DSO_TYPE_USER) { + GElf_Shdr shdr; + ss->adjust_symbols = (ehdr.e_type == ET_EXEC || + elf_section_by_name(elf, &ehdr, &shdr, + ".gnu.prelink_undo", + NULL) != NULL); + } else { + ss->adjust_symbols = 0; + } + + ss->name = strdup(name); + if (!ss->name) + goto out_elf_end; + + ss->elf = elf; + ss->fd = fd; + ss->ehdr = ehdr; + ss->type = type; + + return 0; + +out_elf_end: + elf_end(elf); +out_close: + close(fd); + return err; +} + +int dso__load_sym(struct dso *dso, struct map *map, + struct symsrc *syms_ss, struct symsrc *runtime_ss, + symbol_filter_t filter, int kmodule) +{ + struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; + struct map *curr_map = map; + struct dso *curr_dso = dso; + Elf_Data *symstrs, *secstrs; + uint32_t nr_syms; + int err = -1; + uint32_t idx; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *syms, *opddata = NULL; + GElf_Sym sym; + Elf_Scn *sec, *sec_strndx; + Elf *elf; + int nr = 0; + + dso->symtab_type = syms_ss->type; + + if (!syms_ss->symtab) { + syms_ss->symtab = syms_ss->dynsym; + syms_ss->symshdr = syms_ss->dynshdr; + } + + elf = syms_ss->elf; + ehdr = syms_ss->ehdr; + sec = syms_ss->symtab; + shdr = syms_ss->symshdr; + + if (runtime_ss->opdsec) + opddata = elf_rawdata(runtime_ss->opdsec, NULL); + + syms = elf_getdata(sec, NULL); + if (syms == NULL) + goto out_elf_end; + + sec = elf_getscn(elf, shdr.sh_link); + if (sec == NULL) + goto out_elf_end; + + symstrs = elf_getdata(sec, NULL); + if (symstrs == NULL) + goto out_elf_end; + + sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs = elf_getdata(sec_strndx, NULL); + if (secstrs == NULL) + goto out_elf_end; + + nr_syms = shdr.sh_size / shdr.sh_entsize; + + memset(&sym, 0, sizeof(sym)); + dso->adjust_symbols = runtime_ss->adjust_symbols; + elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { + struct symbol *f; + const char *elf_name = elf_sym__name(&sym, symstrs); + char *demangled = NULL; + int is_label = elf_sym__is_label(&sym); + const char *section_name; + bool used_opd = false; + + if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && + strcmp(elf_name, kmap->ref_reloc_sym->name) == 0) + kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; + + if (!is_label && !elf_sym__is_a(&sym, map->type)) + continue; + + /* Reject ARM ELF "mapping symbols": these aren't unique and + * don't identify functions, so will confuse the profile + * output: */ + if (ehdr.e_machine == EM_ARM) { + if (!strcmp(elf_name, "$a") || + !strcmp(elf_name, "$d") || + !strcmp(elf_name, "$t")) + continue; + } + + if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) { + u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr; + u64 *opd = opddata->d_buf + offset; + sym.st_value = DSO__SWAP(dso, u64, *opd); + sym.st_shndx = elf_addr_to_index(runtime_ss->elf, + sym.st_value); + used_opd = true; + } + + sec = elf_getscn(runtime_ss->elf, sym.st_shndx); + if (!sec) + goto out_elf_end; + + gelf_getshdr(sec, &shdr); + + if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) + continue; + + section_name = elf_sec__name(&shdr, secstrs); + + /* On ARM, symbols for thumb functions have 1 added to + * the symbol address as a flag - remove it */ + if ((ehdr.e_machine == EM_ARM) && + (map->type == MAP__FUNCTION) && + (sym.st_value & 1)) + --sym.st_value; + + if (dso->kernel != DSO_TYPE_USER || kmodule) { + char dso_name[PATH_MAX]; + + if (strcmp(section_name, + (curr_dso->short_name + + dso->short_name_len)) == 0) + goto new_symbol; + + if (strcmp(section_name, ".text") == 0) { + curr_map = map; + curr_dso = dso; + goto new_symbol; + } + + snprintf(dso_name, sizeof(dso_name), + "%s%s", dso->short_name, section_name); + + curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name); + if (curr_map == NULL) { + u64 start = sym.st_value; + + if (kmodule) + start += map->start + shdr.sh_offset; + + curr_dso = dso__new(dso_name); + if (curr_dso == NULL) + goto out_elf_end; + curr_dso->kernel = dso->kernel; + curr_dso->long_name = dso->long_name; + curr_dso->long_name_len = dso->long_name_len; + curr_map = map__new2(start, curr_dso, + map->type); + if (curr_map == NULL) { + dso__delete(curr_dso); + goto out_elf_end; + } + curr_map->map_ip = identity__map_ip; + curr_map->unmap_ip = identity__map_ip; + curr_dso->symtab_type = dso->symtab_type; + map_groups__insert(kmap->kmaps, curr_map); + dsos__add(&dso->node, curr_dso); + dso__set_loaded(curr_dso, map->type); + } else + curr_dso = curr_map->dso; + + goto new_symbol; + } + + if ((used_opd && runtime_ss->adjust_symbols) + || (!used_opd && syms_ss->adjust_symbols)) { + pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " + "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, + (u64)sym.st_value, (u64)shdr.sh_addr, + (u64)shdr.sh_offset); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + } + /* + * We need to figure out if the object was created from C++ sources + * DWARF DW_compile_unit has this, but we don't always have access + * to it... + */ + demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI); + if (demangled != NULL) + elf_name = demangled; +new_symbol: + f = symbol__new(sym.st_value, sym.st_size, + GELF_ST_BIND(sym.st_info), elf_name); + free(demangled); + if (!f) + goto out_elf_end; + + if (filter && filter(curr_map, f)) + symbol__delete(f); + else { + symbols__insert(&curr_dso->symbols[curr_map->type], f); + nr++; + } + } + + /* + * For misannotated, zeroed, ASM function sizes. + */ + if (nr > 0) { + symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols[map->type]); + if (kmap) { + /* + * We need to fixup this here too because we create new + * maps here, for things like vsyscall sections. + */ + __map_groups__fixup_end(kmap->kmaps, map->type); + } + } + err = nr; +out_elf_end: + return err; +} + +void symbol__elf_init(void) +{ + elf_version(EV_CURRENT); +} diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c new file mode 100644 index 000000000000..259f8f2ea9c9 --- /dev/null +++ b/tools/perf/util/symbol-minimal.c @@ -0,0 +1,307 @@ +#include "symbol.h" + +#include <elf.h> +#include <stdio.h> +#include <fcntl.h> +#include <string.h> +#include <byteswap.h> +#include <sys/stat.h> + + +static bool check_need_swap(int file_endian) +{ + const int data = 1; + u8 *check = (u8 *)&data; + int host_endian; + + if (check[0] == 1) + host_endian = ELFDATA2LSB; + else + host_endian = ELFDATA2MSB; + + return host_endian != file_endian; +} + +#define NOTE_ALIGN(sz) (((sz) + 3) & ~3) + +#define NT_GNU_BUILD_ID 3 + +static int read_build_id(void *note_data, size_t note_len, void *bf, + size_t size, bool need_swap) +{ + struct { + u32 n_namesz; + u32 n_descsz; + u32 n_type; + } *nhdr; + void *ptr; + + ptr = note_data; + while (ptr < (note_data + note_len)) { + const char *name; + size_t namesz, descsz; + + nhdr = ptr; + if (need_swap) { + nhdr->n_namesz = bswap_32(nhdr->n_namesz); + nhdr->n_descsz = bswap_32(nhdr->n_descsz); + nhdr->n_type = bswap_32(nhdr->n_type); + } + + namesz = NOTE_ALIGN(nhdr->n_namesz); + descsz = NOTE_ALIGN(nhdr->n_descsz); + + ptr += sizeof(*nhdr); + name = ptr; + ptr += namesz; + if (nhdr->n_type == NT_GNU_BUILD_ID && + nhdr->n_namesz == sizeof("GNU")) { + if (memcmp(name, "GNU", sizeof("GNU")) == 0) { + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + return 0; + } + } + ptr += descsz; + } + + return -1; +} + +int filename__read_debuglink(const char *filename __maybe_unused, + char *debuglink __maybe_unused, + size_t size __maybe_unused) +{ + return -1; +} + +/* + * Just try PT_NOTE header otherwise fails + */ +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + FILE *fp; + int ret = -1; + bool need_swap = false; + u8 e_ident[EI_NIDENT]; + size_t buf_size; + void *buf; + int i; + + fp = fopen(filename, "r"); + if (fp == NULL) + return -1; + + if (fread(e_ident, sizeof(e_ident), 1, fp) != 1) + goto out; + + if (memcmp(e_ident, ELFMAG, SELFMAG) || + e_ident[EI_VERSION] != EV_CURRENT) + goto out; + + need_swap = check_need_swap(e_ident[EI_DATA]); + + /* for simplicity */ + fseek(fp, 0, SEEK_SET); + + if (e_ident[EI_CLASS] == ELFCLASS32) { + Elf32_Ehdr ehdr; + Elf32_Phdr *phdr; + + if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) + goto out; + + if (need_swap) { + ehdr.e_phoff = bswap_32(ehdr.e_phoff); + ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); + ehdr.e_phnum = bswap_16(ehdr.e_phnum); + } + + buf_size = ehdr.e_phentsize * ehdr.e_phnum; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + fseek(fp, ehdr.e_phoff, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + void *tmp; + + if (need_swap) { + phdr->p_type = bswap_32(phdr->p_type); + phdr->p_offset = bswap_32(phdr->p_offset); + phdr->p_filesz = bswap_32(phdr->p_filesz); + } + + if (phdr->p_type != PT_NOTE) + continue; + + buf_size = phdr->p_filesz; + tmp = realloc(buf, buf_size); + if (tmp == NULL) + goto out_free; + + buf = tmp; + fseek(fp, phdr->p_offset, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + ret = read_build_id(buf, buf_size, bf, size, need_swap); + if (ret == 0) + ret = size; + break; + } + } else { + Elf64_Ehdr ehdr; + Elf64_Phdr *phdr; + + if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) + goto out; + + if (need_swap) { + ehdr.e_phoff = bswap_64(ehdr.e_phoff); + ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); + ehdr.e_phnum = bswap_16(ehdr.e_phnum); + } + + buf_size = ehdr.e_phentsize * ehdr.e_phnum; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + fseek(fp, ehdr.e_phoff, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + void *tmp; + + if (need_swap) { + phdr->p_type = bswap_32(phdr->p_type); + phdr->p_offset = bswap_64(phdr->p_offset); + phdr->p_filesz = bswap_64(phdr->p_filesz); + } + + if (phdr->p_type != PT_NOTE) + continue; + + buf_size = phdr->p_filesz; + tmp = realloc(buf, buf_size); + if (tmp == NULL) + goto out_free; + + buf = tmp; + fseek(fp, phdr->p_offset, SEEK_SET); + if (fread(buf, buf_size, 1, fp) != 1) + goto out_free; + + ret = read_build_id(buf, buf_size, bf, size, need_swap); + if (ret == 0) + ret = size; + break; + } + } +out_free: + free(buf); +out: + fclose(fp); + return ret; +} + +int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +{ + int fd; + int ret = -1; + struct stat stbuf; + size_t buf_size; + void *buf; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -1; + + if (fstat(fd, &stbuf) < 0) + goto out; + + buf_size = stbuf.st_size; + buf = malloc(buf_size); + if (buf == NULL) + goto out; + + if (read(fd, buf, buf_size) != (ssize_t) buf_size) + goto out_free; + + ret = read_build_id(buf, buf_size, build_id, size, false); +out_free: + free(buf); +out: + close(fd); + return ret; +} + +int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused, + const char *name, + enum dso_binary_type type) +{ + int fd = open(name, O_RDONLY); + if (fd < 0) + return -1; + + ss->name = strdup(name); + if (!ss->name) + goto out_close; + + ss->type = type; + + return 0; +out_close: + close(fd); + return -1; +} + +bool symsrc__possibly_runtime(struct symsrc *ss __maybe_unused) +{ + /* Assume all sym sources could be a runtime image. */ + return true; +} + +bool symsrc__has_symtab(struct symsrc *ss __maybe_unused) +{ + return false; +} + +void symsrc__destroy(struct symsrc *ss) +{ + free(ss->name); + close(ss->fd); +} + +int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, + struct symsrc *ss __maybe_unused, + struct map *map __maybe_unused, + symbol_filter_t filter __maybe_unused) +{ + return 0; +} + +int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, + struct symsrc *ss, + struct symsrc *runtime_ss __maybe_unused, + symbol_filter_t filter __maybe_unused, + int kmodule __maybe_unused) +{ + unsigned char *build_id[BUILD_ID_SIZE]; + + if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { + dso__set_build_id(dso, build_id); + return 1; + } + return 0; +} + +void symbol__elf_init(void) +{ +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 8b63b678e127..e2e8c697cffe 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -15,8 +15,6 @@ #include "symbol.h" #include "strlist.h" -#include <libelf.h> -#include <gelf.h> #include <elf.h> #include <limits.h> #include <sys/utsname.h> @@ -25,15 +23,7 @@ #define KSYM_NAME_LEN 256 #endif -#ifndef NT_GNU_BUILD_ID -#define NT_GNU_BUILD_ID 3 -#endif - static void dso_cache__free(struct rb_root *root); -static bool dso__build_id_equal(const struct dso *dso, u8 *build_id); -static int elf_read_build_id(Elf *elf, void *bf, size_t size); -static void dsos__add(struct list_head *head, struct dso *dso); -static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, @@ -170,7 +160,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) return SYMBOL_B; } -static void symbols__fixup_duplicate(struct rb_root *symbols) +void symbols__fixup_duplicate(struct rb_root *symbols) { struct rb_node *nd; struct symbol *curr, *next; @@ -199,7 +189,7 @@ again: } } -static void symbols__fixup_end(struct rb_root *symbols) +void symbols__fixup_end(struct rb_root *symbols) { struct rb_node *nd, *prevnd = rb_first(symbols); struct symbol *curr, *prev; @@ -222,7 +212,7 @@ static void symbols__fixup_end(struct rb_root *symbols) curr->end = roundup(curr->start, 4096); } -static void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) +void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) { struct map *prev, *curr; struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]); @@ -252,8 +242,7 @@ static void map_groups__fixup_end(struct map_groups *mg) __map_groups__fixup_end(mg, i); } -static struct symbol *symbol__new(u64 start, u64 len, u8 binding, - const char *name) +struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) { size_t namelen = strlen(name) + 1; struct symbol *sym = calloc(1, (symbol_conf.priv_size + @@ -390,7 +379,7 @@ void dso__set_build_id(struct dso *dso, void *build_id) dso->has_build_id = 1; } -static void symbols__insert(struct rb_root *symbols, struct symbol *sym) +void symbols__insert(struct rb_root *symbols, struct symbol *sym) { struct rb_node **p = &symbols->rb_node; struct rb_node *parent = NULL; @@ -574,7 +563,7 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, - char type, u64 start, u64 end)) + char type, u64 start)) { char *line = NULL; size_t n; @@ -614,13 +603,8 @@ int kallsyms__parse(const char *filename, void *arg, break; } - /* - * module symbols are not sorted so we add all - * symbols with zero length and rely on - * symbols__fixup_end() to fix it up. - */ err = process_symbol(arg, symbol_name, - symbol_type, start, start); + symbol_type, start); if (err) break; } @@ -647,7 +631,7 @@ static u8 kallsyms2elf_type(char type) } static int map__process_kallsym_symbol(void *arg, const char *name, - char type, u64 start, u64 end) + char type, u64 start) { struct symbol *sym; struct process_kallsyms_args *a = arg; @@ -656,8 +640,12 @@ static int map__process_kallsym_symbol(void *arg, const char *name, if (!symbol_type__is_a(type, a->map->type)) return 0; - sym = symbol__new(start, end - start + 1, - kallsyms2elf_type(type), name); + /* + * module symbols are not sorted so we add all + * symbols, setting length to 0, and rely on + * symbols__fixup_end() to fix it up. + */ + sym = symbol__new(start, 0, kallsyms2elf_type(type), name); if (sym == NULL) return -ENOMEM; /* @@ -904,556 +892,7 @@ out_failure: return -1; } -/** - * elf_symtab__for_each_symbol - iterate thru all the symbols - * - * @syms: struct elf_symtab instance to iterate - * @idx: uint32_t idx - * @sym: GElf_Sym iterator - */ -#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \ - for (idx = 0, gelf_getsym(syms, idx, &sym);\ - idx < nr_syms; \ - idx++, gelf_getsym(syms, idx, &sym)) - -static inline uint8_t elf_sym__type(const GElf_Sym *sym) -{ - return GELF_ST_TYPE(sym->st_info); -} - -static inline int elf_sym__is_function(const GElf_Sym *sym) -{ - return elf_sym__type(sym) == STT_FUNC && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF; -} - -static inline bool elf_sym__is_object(const GElf_Sym *sym) -{ - return elf_sym__type(sym) == STT_OBJECT && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF; -} - -static inline int elf_sym__is_label(const GElf_Sym *sym) -{ - return elf_sym__type(sym) == STT_NOTYPE && - sym->st_name != 0 && - sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; -} - -static inline const char *elf_sec__name(const GElf_Shdr *shdr, - const Elf_Data *secstrs) -{ - return secstrs->d_buf + shdr->sh_name; -} - -static inline int elf_sec__is_text(const GElf_Shdr *shdr, - const Elf_Data *secstrs) -{ - return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; -} - -static inline bool elf_sec__is_data(const GElf_Shdr *shdr, - const Elf_Data *secstrs) -{ - return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; -} - -static inline const char *elf_sym__name(const GElf_Sym *sym, - const Elf_Data *symstrs) -{ - return symstrs->d_buf + sym->st_name; -} - -static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, - GElf_Shdr *shp, const char *name, - size_t *idx) -{ - Elf_Scn *sec = NULL; - size_t cnt = 1; - - while ((sec = elf_nextscn(elf, sec)) != NULL) { - char *str; - - gelf_getshdr(sec, shp); - str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); - if (!strcmp(name, str)) { - if (idx) - *idx = cnt; - break; - } - ++cnt; - } - - return sec; -} - -#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) - -#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ - for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ - idx < nr_entries; \ - ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) - -/* - * We need to check if we have a .dynsym, so that we can handle the - * .plt, synthesizing its symbols, that aren't on the symtabs (be it - * .dynsym or .symtab). - * And always look at the original dso, not at debuginfo packages, that - * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). - */ -static int -dso__synthesize_plt_symbols(struct dso *dso, char *name, struct map *map, - symbol_filter_t filter) -{ - uint32_t nr_rel_entries, idx; - GElf_Sym sym; - u64 plt_offset; - GElf_Shdr shdr_plt; - struct symbol *f; - GElf_Shdr shdr_rel_plt, shdr_dynsym; - Elf_Data *reldata, *syms, *symstrs; - Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym; - size_t dynsym_idx; - GElf_Ehdr ehdr; - char sympltname[1024]; - Elf *elf; - int nr = 0, symidx, fd, err = 0; - - fd = open(name, O_RDONLY); - if (fd < 0) - goto out; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) - goto out_close; - - if (gelf_getehdr(elf, &ehdr) == NULL) - goto out_elf_end; - - scn_dynsym = elf_section_by_name(elf, &ehdr, &shdr_dynsym, - ".dynsym", &dynsym_idx); - if (scn_dynsym == NULL) - goto out_elf_end; - - scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, - ".rela.plt", NULL); - if (scn_plt_rel == NULL) { - scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt, - ".rel.plt", NULL); - if (scn_plt_rel == NULL) - goto out_elf_end; - } - - err = -1; - - if (shdr_rel_plt.sh_link != dynsym_idx) - goto out_elf_end; - - if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL) - goto out_elf_end; - - /* - * Fetch the relocation section to find the idxes to the GOT - * and the symbols in the .dynsym they refer to. - */ - reldata = elf_getdata(scn_plt_rel, NULL); - if (reldata == NULL) - goto out_elf_end; - - syms = elf_getdata(scn_dynsym, NULL); - if (syms == NULL) - goto out_elf_end; - - scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link); - if (scn_symstrs == NULL) - goto out_elf_end; - - symstrs = elf_getdata(scn_symstrs, NULL); - if (symstrs == NULL) - goto out_elf_end; - - nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; - plt_offset = shdr_plt.sh_offset; - - if (shdr_rel_plt.sh_type == SHT_RELA) { - GElf_Rela pos_mem, *pos; - - elf_section__for_each_rela(reldata, pos, pos_mem, idx, - nr_rel_entries) { - symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; - gelf_getsym(syms, symidx, &sym); - snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); - - f = symbol__new(plt_offset, shdr_plt.sh_entsize, - STB_GLOBAL, sympltname); - if (!f) - goto out_elf_end; - - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&dso->symbols[map->type], f); - ++nr; - } - } - } else if (shdr_rel_plt.sh_type == SHT_REL) { - GElf_Rel pos_mem, *pos; - elf_section__for_each_rel(reldata, pos, pos_mem, idx, - nr_rel_entries) { - symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; - gelf_getsym(syms, symidx, &sym); - snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); - - f = symbol__new(plt_offset, shdr_plt.sh_entsize, - STB_GLOBAL, sympltname); - if (!f) - goto out_elf_end; - - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&dso->symbols[map->type], f); - ++nr; - } - } - } - - err = 0; -out_elf_end: - elf_end(elf); -out_close: - close(fd); - - if (err == 0) - return nr; -out: - pr_debug("%s: problems reading %s PLT info.\n", - __func__, dso->long_name); - return 0; -} - -static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) -{ - switch (type) { - case MAP__FUNCTION: - return elf_sym__is_function(sym); - case MAP__VARIABLE: - return elf_sym__is_object(sym); - default: - return false; - } -} - -static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs, - enum map_type type) -{ - switch (type) { - case MAP__FUNCTION: - return elf_sec__is_text(shdr, secstrs); - case MAP__VARIABLE: - return elf_sec__is_data(shdr, secstrs); - default: - return false; - } -} - -static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) -{ - Elf_Scn *sec = NULL; - GElf_Shdr shdr; - size_t cnt = 1; - - while ((sec = elf_nextscn(elf, sec)) != NULL) { - gelf_getshdr(sec, &shdr); - - if ((addr >= shdr.sh_addr) && - (addr < (shdr.sh_addr + shdr.sh_size))) - return cnt; - - ++cnt; - } - - return -1; -} - -static int dso__swap_init(struct dso *dso, unsigned char eidata) -{ - static unsigned int const endian = 1; - - dso->needs_swap = DSO_SWAP__NO; - - switch (eidata) { - case ELFDATA2LSB: - /* We are big endian, DSO is little endian. */ - if (*(unsigned char const *)&endian != 1) - dso->needs_swap = DSO_SWAP__YES; - break; - - case ELFDATA2MSB: - /* We are little endian, DSO is big endian. */ - if (*(unsigned char const *)&endian != 0) - dso->needs_swap = DSO_SWAP__YES; - break; - - default: - pr_err("unrecognized DSO data encoding %d\n", eidata); - return -EINVAL; - } - - return 0; -} - -static int dso__load_sym(struct dso *dso, struct map *map, const char *name, - int fd, symbol_filter_t filter, int kmodule, - int want_symtab) -{ - struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; - struct map *curr_map = map; - struct dso *curr_dso = dso; - Elf_Data *symstrs, *secstrs; - uint32_t nr_syms; - int err = -1; - uint32_t idx; - GElf_Ehdr ehdr; - GElf_Shdr shdr, opdshdr; - Elf_Data *syms, *opddata = NULL; - GElf_Sym sym; - Elf_Scn *sec, *sec_strndx, *opdsec; - Elf *elf; - int nr = 0; - size_t opdidx = 0; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug("%s: cannot read %s ELF file.\n", __func__, name); - goto out_close; - } - - if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_debug("%s: cannot get elf header.\n", __func__); - goto out_elf_end; - } - - if (dso__swap_init(dso, ehdr.e_ident[EI_DATA])) - goto out_elf_end; - - /* Always reject images with a mismatched build-id: */ - if (dso->has_build_id) { - u8 build_id[BUILD_ID_SIZE]; - - if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) - goto out_elf_end; - - if (!dso__build_id_equal(dso, build_id)) - goto out_elf_end; - } - - sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL); - if (sec == NULL) { - if (want_symtab) - goto out_elf_end; - - sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL); - if (sec == NULL) - goto out_elf_end; - } - - opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx); - if (opdshdr.sh_type != SHT_PROGBITS) - opdsec = NULL; - if (opdsec) - opddata = elf_rawdata(opdsec, NULL); - - syms = elf_getdata(sec, NULL); - if (syms == NULL) - goto out_elf_end; - - sec = elf_getscn(elf, shdr.sh_link); - if (sec == NULL) - goto out_elf_end; - - symstrs = elf_getdata(sec, NULL); - if (symstrs == NULL) - goto out_elf_end; - - sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); - if (sec_strndx == NULL) - goto out_elf_end; - - secstrs = elf_getdata(sec_strndx, NULL); - if (secstrs == NULL) - goto out_elf_end; - - nr_syms = shdr.sh_size / shdr.sh_entsize; - - memset(&sym, 0, sizeof(sym)); - if (dso->kernel == DSO_TYPE_USER) { - dso->adjust_symbols = (ehdr.e_type == ET_EXEC || - elf_section_by_name(elf, &ehdr, &shdr, - ".gnu.prelink_undo", - NULL) != NULL); - } else { - dso->adjust_symbols = 0; - } - elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { - struct symbol *f; - const char *elf_name = elf_sym__name(&sym, symstrs); - char *demangled = NULL; - int is_label = elf_sym__is_label(&sym); - const char *section_name; - - if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && - strcmp(elf_name, kmap->ref_reloc_sym->name) == 0) - kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; - - if (!is_label && !elf_sym__is_a(&sym, map->type)) - continue; - - /* Reject ARM ELF "mapping symbols": these aren't unique and - * don't identify functions, so will confuse the profile - * output: */ - if (ehdr.e_machine == EM_ARM) { - if (!strcmp(elf_name, "$a") || - !strcmp(elf_name, "$d") || - !strcmp(elf_name, "$t")) - continue; - } - - if (opdsec && sym.st_shndx == opdidx) { - u32 offset = sym.st_value - opdshdr.sh_addr; - u64 *opd = opddata->d_buf + offset; - sym.st_value = DSO__SWAP(dso, u64, *opd); - sym.st_shndx = elf_addr_to_index(elf, sym.st_value); - } - - sec = elf_getscn(elf, sym.st_shndx); - if (!sec) - goto out_elf_end; - - gelf_getshdr(sec, &shdr); - - if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) - continue; - - section_name = elf_sec__name(&shdr, secstrs); - - /* On ARM, symbols for thumb functions have 1 added to - * the symbol address as a flag - remove it */ - if ((ehdr.e_machine == EM_ARM) && - (map->type == MAP__FUNCTION) && - (sym.st_value & 1)) - --sym.st_value; - - if (dso->kernel != DSO_TYPE_USER || kmodule) { - char dso_name[PATH_MAX]; - - if (strcmp(section_name, - (curr_dso->short_name + - dso->short_name_len)) == 0) - goto new_symbol; - - if (strcmp(section_name, ".text") == 0) { - curr_map = map; - curr_dso = dso; - goto new_symbol; - } - - snprintf(dso_name, sizeof(dso_name), - "%s%s", dso->short_name, section_name); - - curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name); - if (curr_map == NULL) { - u64 start = sym.st_value; - - if (kmodule) - start += map->start + shdr.sh_offset; - - curr_dso = dso__new(dso_name); - if (curr_dso == NULL) - goto out_elf_end; - curr_dso->kernel = dso->kernel; - curr_dso->long_name = dso->long_name; - curr_dso->long_name_len = dso->long_name_len; - curr_map = map__new2(start, curr_dso, - map->type); - if (curr_map == NULL) { - dso__delete(curr_dso); - goto out_elf_end; - } - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; - curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmap->kmaps, curr_map); - dsos__add(&dso->node, curr_dso); - dso__set_loaded(curr_dso, map->type); - } else - curr_dso = curr_map->dso; - - goto new_symbol; - } - - if (curr_dso->adjust_symbols) { - pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " - "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, - (u64)sym.st_value, (u64)shdr.sh_addr, - (u64)shdr.sh_offset); - sym.st_value -= shdr.sh_addr - shdr.sh_offset; - } - /* - * We need to figure out if the object was created from C++ sources - * DWARF DW_compile_unit has this, but we don't always have access - * to it... - */ - demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI); - if (demangled != NULL) - elf_name = demangled; -new_symbol: - f = symbol__new(sym.st_value, sym.st_size, - GELF_ST_BIND(sym.st_info), elf_name); - free(demangled); - if (!f) - goto out_elf_end; - - if (filter && filter(curr_map, f)) - symbol__delete(f); - else { - symbols__insert(&curr_dso->symbols[curr_map->type], f); - nr++; - } - } - - /* - * For misannotated, zeroed, ASM function sizes. - */ - if (nr > 0) { - symbols__fixup_duplicate(&dso->symbols[map->type]); - symbols__fixup_end(&dso->symbols[map->type]); - if (kmap) { - /* - * We need to fixup this here too because we create new - * maps here, for things like vsyscall sections. - */ - __map_groups__fixup_end(kmap->kmaps, map->type); - } - } - err = nr; -out_elf_end: - elf_end(elf); -out_close: - return err; -} - -static bool dso__build_id_equal(const struct dso *dso, u8 *build_id) +bool dso__build_id_equal(const struct dso *dso, u8 *build_id) { return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0; } @@ -1480,216 +919,11 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) return have_build_id; } -/* - * Align offset to 4 bytes as needed for note name and descriptor data. - */ -#define NOTE_ALIGN(n) (((n) + 3) & -4U) - -static int elf_read_build_id(Elf *elf, void *bf, size_t size) -{ - int err = -1; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - Elf_Data *data; - Elf_Scn *sec; - Elf_Kind ek; - void *ptr; - - if (size < BUILD_ID_SIZE) - goto out; - - ek = elf_kind(elf); - if (ek != ELF_K_ELF) - goto out; - - if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_err("%s: cannot get elf header.\n", __func__); - goto out; - } - - /* - * Check following sections for notes: - * '.note.gnu.build-id' - * '.notes' - * '.note' (VDSO specific) - */ - do { - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".note.gnu.build-id", NULL); - if (sec) - break; - - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".notes", NULL); - if (sec) - break; - - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".note", NULL); - if (sec) - break; - - return err; - - } while (0); - - data = elf_getdata(sec, NULL); - if (data == NULL) - goto out; - - ptr = data->d_buf; - while (ptr < (data->d_buf + data->d_size)) { - GElf_Nhdr *nhdr = ptr; - size_t namesz = NOTE_ALIGN(nhdr->n_namesz), - descsz = NOTE_ALIGN(nhdr->n_descsz); - const char *name; - - ptr += sizeof(*nhdr); - name = ptr; - ptr += namesz; - if (nhdr->n_type == NT_GNU_BUILD_ID && - nhdr->n_namesz == sizeof("GNU")) { - if (memcmp(name, "GNU", sizeof("GNU")) == 0) { - size_t sz = min(size, descsz); - memcpy(bf, ptr, sz); - memset(bf + sz, 0, size - sz); - err = descsz; - break; - } - } - ptr += descsz; - } - -out: - return err; -} - -int filename__read_build_id(const char *filename, void *bf, size_t size) -{ - int fd, err = -1; - Elf *elf; - - if (size < BUILD_ID_SIZE) - goto out; - - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); - goto out_close; - } - - err = elf_read_build_id(elf, bf, size); - - elf_end(elf); -out_close: - close(fd); -out: - return err; -} - -int sysfs__read_build_id(const char *filename, void *build_id, size_t size) -{ - int fd, err = -1; - - if (size < BUILD_ID_SIZE) - goto out; - - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; - - while (1) { - char bf[BUFSIZ]; - GElf_Nhdr nhdr; - size_t namesz, descsz; - - if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) - break; - - namesz = NOTE_ALIGN(nhdr.n_namesz); - descsz = NOTE_ALIGN(nhdr.n_descsz); - if (nhdr.n_type == NT_GNU_BUILD_ID && - nhdr.n_namesz == sizeof("GNU")) { - if (read(fd, bf, namesz) != (ssize_t)namesz) - break; - if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { - size_t sz = min(descsz, size); - if (read(fd, build_id, sz) == (ssize_t)sz) { - memset(build_id + sz, 0, size - sz); - err = 0; - break; - } - } else if (read(fd, bf, descsz) != (ssize_t)descsz) - break; - } else { - int n = namesz + descsz; - if (read(fd, bf, n) != n) - break; - } - } - close(fd); -out: - return err; -} - -static int filename__read_debuglink(const char *filename, - char *debuglink, size_t size) -{ - int fd, err = -1; - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - Elf_Data *data; - Elf_Scn *sec; - Elf_Kind ek; - - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); - goto out_close; - } - - ek = elf_kind(elf); - if (ek != ELF_K_ELF) - goto out_close; - - if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_err("%s: cannot get elf header.\n", __func__); - goto out_close; - } - - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".gnu_debuglink", NULL); - if (sec == NULL) - goto out_close; - - data = elf_getdata(sec, NULL); - if (data == NULL) - goto out_close; - - /* the start of this section is a zero-terminated string */ - strncpy(debuglink, data->d_buf, size); - - elf_end(elf); - -out_close: - close(fd); -out: - return err; -} - char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { [DSO_BINARY_TYPE__KALLSYMS] = 'k', + [DSO_BINARY_TYPE__VMLINUX] = 'v', [DSO_BINARY_TYPE__JAVA_JIT] = 'j', [DSO_BINARY_TYPE__DEBUGLINK] = 'l', [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', @@ -1700,6 +934,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', }; if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) @@ -1775,7 +1010,9 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, default: case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__JAVA_JIT: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; @@ -1789,11 +1026,12 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { char *name; int ret = -1; - int fd; u_int i; struct machine *machine; char *root_dir = (char *) ""; - int want_symtab; + int ss_pos = 0; + struct symsrc ss_[2]; + struct symsrc *syms_ss = NULL, *runtime_ss = NULL; dso__set_loaded(dso, map->type); @@ -1835,54 +1073,69 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) root_dir = machine->root_dir; /* Iterate over candidate debug images. - * On the first pass, only load images if they have a full symtab. - * Failing that, do a second pass where we accept .dynsym also + * Keep track of "interesting" ones (those which have a symtab, dynsym, + * and/or opd section) for processing. */ - want_symtab = 1; -restart: for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) { + struct symsrc *ss = &ss_[ss_pos]; + bool next_slot = false; - dso->symtab_type = binary_type_symtab[i]; + enum dso_binary_type symtab_type = binary_type_symtab[i]; - if (dso__binary_type_file(dso, dso->symtab_type, + if (dso__binary_type_file(dso, symtab_type, root_dir, name, PATH_MAX)) continue; /* Name is now the name of the next image to try */ - fd = open(name, O_RDONLY); - if (fd < 0) + if (symsrc__init(ss, dso, name, symtab_type) < 0) continue; - ret = dso__load_sym(dso, map, name, fd, filter, 0, - want_symtab); - close(fd); + if (!syms_ss && symsrc__has_symtab(ss)) { + syms_ss = ss; + next_slot = true; + } - /* - * Some people seem to have debuginfo files _WITHOUT_ debug - * info!?!? - */ - if (!ret) - continue; + if (!runtime_ss && symsrc__possibly_runtime(ss)) { + runtime_ss = ss; + next_slot = true; + } - if (ret > 0) { - int nr_plt; + if (next_slot) { + ss_pos++; - nr_plt = dso__synthesize_plt_symbols(dso, name, map, filter); - if (nr_plt > 0) - ret += nr_plt; - break; + if (syms_ss && runtime_ss) + break; } + } - /* - * If we wanted a full symtab but no image had one, - * relax our requirements and repeat the search. - */ - if (ret <= 0 && want_symtab) { - want_symtab = 0; - goto restart; + if (!runtime_ss && !syms_ss) + goto out_free; + + if (runtime_ss && !syms_ss) { + syms_ss = runtime_ss; + } + + /* We'll have to hope for the best */ + if (!runtime_ss && syms_ss) + runtime_ss = syms_ss; + + if (syms_ss) + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0); + else + ret = -1; + + if (ret > 0) { + int nr_plt; + + nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter); + if (nr_plt > 0) + ret += nr_plt; } + for (; ss_pos > 0; ss_pos--) + symsrc__destroy(&ss_[ss_pos - 1]); +out_free: free(name); if (ret < 0 && strstr(dso->name, " (deleted)") != NULL) return 0; @@ -2030,25 +1283,6 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); } -/* - * Constructor variant for modules (where we know from /proc/modules where - * they are loaded) and for vmlinux, where only after we load all the - * symbols we'll know where it starts and ends. - */ -static struct map *map__new2(u64 start, struct dso *dso, enum map_type type) -{ - struct map *map = calloc(1, (sizeof(*map) + - (dso->kernel ? sizeof(struct kmap) : 0))); - if (map != NULL) { - /* - * ->end will be filled after we load all the symbols - */ - map__init(map, type, start, 0, 0, dso); - } - - return map; -} - struct map *machine__new_module(struct machine *machine, u64 start, const char *filename) { @@ -2141,22 +1375,30 @@ out_failure: int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, symbol_filter_t filter) { - int err = -1, fd; + int err = -1; + struct symsrc ss; char symfs_vmlinux[PATH_MAX]; + enum dso_binary_type symtab_type; snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", symbol_conf.symfs, vmlinux); - fd = open(symfs_vmlinux, O_RDONLY); - if (fd < 0) + + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + symtab_type = DSO_BINARY_TYPE__VMLINUX; + + if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) return -1; - dso__set_long_name(dso, (char *)vmlinux); - dso__set_loaded(dso, map->type); - err = dso__load_sym(dso, map, symfs_vmlinux, fd, filter, 0, 0); - close(fd); + err = dso__load_sym(dso, map, &ss, &ss, filter, 0); + symsrc__destroy(&ss); - if (err > 0) + if (err > 0) { + dso__set_long_name(dso, (char *)vmlinux); + dso__set_loaded(dso, map->type); pr_debug("Using %s for symbols\n", symfs_vmlinux); + } return err; } @@ -2173,10 +1415,8 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, filename = dso__build_id_filename(dso, NULL, 0); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, filter); - if (err > 0) { - dso__set_long_name(dso, filename); + if (err > 0) goto out; - } free(filename); } @@ -2291,9 +1531,8 @@ do_kallsyms: free(kallsyms_allocated_filename); if (err > 0) { + dso__set_long_name(dso, strdup("[kernel.kallsyms]")); out_fixup: - if (kallsyms_filename != NULL) - dso__set_long_name(dso, strdup("[kernel.kallsyms]")); map__fixup_start(map); map__fixup_end(map); } @@ -2352,12 +1591,12 @@ out_try_fixup: return err; } -static void dsos__add(struct list_head *head, struct dso *dso) +void dsos__add(struct list_head *head, struct dso *dso) { list_add_tail(&dso->node, head); } -static struct dso *dsos__find(struct list_head *head, const char *name) +struct dso *dsos__find(struct list_head *head, const char *name) { struct dso *pos; @@ -2516,7 +1755,7 @@ struct process_args { }; static int symbol__in_kernel(void *arg, const char *name, - char type __used, u64 start, u64 end __used) + char type __maybe_unused, u64 start) { struct process_args *args = arg; @@ -2752,9 +1991,10 @@ int symbol__init(void) if (symbol_conf.initialized) return 0; - symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64)); + symbol_conf.priv_size = PERF_ALIGN(symbol_conf.priv_size, sizeof(u64)); + + symbol__elf_init(); - elf_version(EV_CURRENT); if (symbol_conf.sort_by_name) symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) - sizeof(struct symbol)); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 1fe733a1e21f..b441b07172b7 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -10,22 +10,31 @@ #include <linux/rbtree.h> #include <stdio.h> #include <byteswap.h> +#include <libgen.h> + +#ifndef NO_LIBELF_SUPPORT +#include <libelf.h> +#include <gelf.h> +#include <elf.h> +#endif #ifdef HAVE_CPLUS_DEMANGLE extern char *cplus_demangle(const char *, int); -static inline char *bfd_demangle(void __used *v, const char *c, int i) +static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) { return cplus_demangle(c, i); } #else #ifdef NO_DEMANGLE -static inline char *bfd_demangle(void __used *v, const char __used *c, - int __used i) +static inline char *bfd_demangle(void __maybe_unused *v, + const char __maybe_unused *c, + int __maybe_unused i) { return NULL; } #else +#define PACKAGE 'perf' #include <bfd.h> #endif #endif @@ -158,6 +167,8 @@ struct addr_location { enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__VMLINUX, + DSO_BINARY_TYPE__GUEST_VMLINUX, DSO_BINARY_TYPE__JAVA_JIT, DSO_BINARY_TYPE__DEBUGLINK, DSO_BINARY_TYPE__BUILD_ID_CACHE, @@ -217,6 +228,36 @@ struct dso { char name[0]; }; +struct symsrc { + char *name; + int fd; + enum dso_binary_type type; + +#ifndef NO_LIBELF_SUPPORT + Elf *elf; + GElf_Ehdr ehdr; + + Elf_Scn *opdsec; + size_t opdidx; + GElf_Shdr opdshdr; + + Elf_Scn *symtab; + GElf_Shdr symshdr; + + Elf_Scn *dynsym; + size_t dynsym_idx; + GElf_Shdr dynshdr; + + bool adjust_symbols; +#endif +}; + +void symsrc__destroy(struct symsrc *ss); +int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, + enum dso_binary_type type); +bool symsrc__has_symtab(struct symsrc *ss); +bool symsrc__possibly_runtime(struct symsrc *ss); + #define DSO__SWAP(dso, type, val) \ ({ \ type ____r = val; \ @@ -254,6 +295,8 @@ static inline void dso__set_loaded(struct dso *dso, enum map_type type) void dso__sort_by_name(struct dso *dso, enum map_type type); +void dsos__add(struct list_head *head, struct dso *dso); +struct dso *dsos__find(struct list_head *head, const char *name); struct dso *__dsos__findnew(struct list_head *head, const char *name); int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter); @@ -283,6 +326,7 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); char dso__symtab_origin(const struct dso *dso); void dso__set_long_name(struct dso *dso, char *name); void dso__set_build_id(struct dso *dso, void *build_id); +bool dso__build_id_equal(const struct dso *dso, u8 *build_id); void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine); struct map *dso__new_map(const char *name); @@ -297,7 +341,9 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits); int build_id__sprintf(const u8 *build_id, int len, char *bf); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, - char type, u64 start, u64 end)); + char type, u64 start)); +int filename__read_debuglink(const char *filename, char *debuglink, + size_t size); void machine__destroy_kernel_maps(struct machine *machine); int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); @@ -309,6 +355,8 @@ void machines__destroy_guest_kernel_maps(struct rb_root *machines); int symbol__init(void); void symbol__exit(void); +void symbol__elf_init(void); +struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); @@ -326,4 +374,15 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); int dso__test_data(void); +int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, + struct symsrc *runtime_ss, symbol_filter_t filter, + int kmodule); +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, + struct map *map, symbol_filter_t filter); + +void symbols__insert(struct rb_root *symbols, struct symbol *sym); +void symbols__fixup_duplicate(struct rb_root *symbols); +void symbols__fixup_end(struct rb_root *symbols); +void __map_groups__fixup_end(struct map_groups *mg, enum map_type type); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 051eaa68095e..065528b7563e 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -117,8 +117,8 @@ int perf_target__strerror(struct perf_target *target, int errnum, if (err != buf) { size_t len = strlen(err); - char *c = mempcpy(buf, err, min(buflen - 1, len)); - *c = '\0'; + memcpy(buf, err, min(buflen - 1, len)); + *(buf + min(buflen - 1, len)) = '\0'; } return 0; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 70c2c13ff679..f66610b7bacf 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -16,6 +16,8 @@ struct thread { bool comm_set; char *comm; int comm_len; + + void *priv; }; struct machine; diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 7eeebcee291c..884dde9b9bc1 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -58,8 +58,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) } if (top->evlist->nr_entries == 1) { - struct perf_evsel *first; - first = list_entry(top->evlist->entries.next, struct perf_evsel, node); + struct perf_evsel *first = perf_evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", (uint64_t)first->attr.sample_period, top->freq ? "Hz" : ""); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 33347ca89ee4..86ff1b15059b 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -5,6 +5,7 @@ #include "types.h" #include <stddef.h> #include <stdbool.h> +#include <termios.h> struct perf_evlist; struct perf_evsel; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 0715c843c2e7..3aabcd687cd5 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -162,25 +162,16 @@ int trace_parse_common_pid(struct pevent *pevent, void *data) return pevent_data_pid(pevent, &record); } -unsigned long long read_size(struct pevent *pevent, void *ptr, int size) +unsigned long long read_size(struct event_format *event, void *ptr, int size) { - return pevent_read_number(pevent, ptr, size); + return pevent_read_number(event->pevent, ptr, size); } -void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) +void event_format__print(struct event_format *event, + int cpu, void *data, int size) { - struct event_format *event; struct pevent_record record; struct trace_seq s; - int type; - - type = trace_parse_common_type(pevent, data); - - event = pevent_find_event(pevent, type); - if (!event) { - warning("ug! no event found for type %d", type); - return; - } memset(&record, 0, sizeof(record)); record.cpu = cpu; @@ -192,6 +183,19 @@ void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) trace_seq_do_printf(&s); } +void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) +{ + int type = trace_parse_common_type(pevent, data); + struct event_format *event = pevent_find_event(pevent, type); + + if (!event) { + warning("ug! no event found for type %d", type); + return; + } + + event_format__print(event, cpu, data, size); +} + void print_event(struct pevent *pevent, int cpu, void *data, int size, unsigned long long nsecs, char *comm) { @@ -217,7 +221,7 @@ void print_event(struct pevent *pevent, int cpu, void *data, int size, } void parse_proc_kallsyms(struct pevent *pevent, - char *file, unsigned int size __unused) + char *file, unsigned int size __maybe_unused) { unsigned long long addr; char *func; @@ -225,31 +229,29 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char ch; + char *fmt; line = strtok_r(file, "\n", &next); while (line) { mod = NULL; - sscanf(line, "%as %c %as\t[%as", - (float *)(void *)&addr_str, /* workaround gcc warning */ - &ch, (float *)(void *)&func, (float *)(void *)&mod); + addr_str = strtok_r(line, " ", &fmt); addr = strtoull(addr_str, NULL, 16); - free(addr_str); - - /* truncate the extra ']' */ + /* skip character */ + strtok_r(NULL, " ", &fmt); + func = strtok_r(NULL, "\t", &fmt); + mod = strtok_r(NULL, "]", &fmt); + /* truncate the extra '[' */ if (mod) - mod[strlen(mod) - 1] = 0; + mod = mod + 1; pevent_register_function(pevent, func, addr, mod); - free(func); - free(mod); line = strtok_r(NULL, "\n", &next); } } void parse_ftrace_printk(struct pevent *pevent, - char *file, unsigned int size __unused) + char *file, unsigned int size __maybe_unused) { unsigned long long addr; char *printk; @@ -289,7 +291,7 @@ struct event_format *trace_find_next_event(struct pevent *pevent, { static int idx; - if (!pevent->events) + if (!pevent || !pevent->events) return NULL; if (!event) { diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 474aa7a7df43..8715a1006d00 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -35,12 +35,11 @@ static int stop_script_unsupported(void) return 0; } -static void process_event_unsupported(union perf_event *event __unused, - struct pevent *pevent __unused, - struct perf_sample *sample __unused, - struct perf_evsel *evsel __unused, - struct machine *machine __unused, - struct thread *thread __unused) +static void process_event_unsupported(union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine __maybe_unused, + struct addr_location *al __maybe_unused) { } @@ -53,17 +52,19 @@ static void print_python_unsupported_msg(void) "\n etc.\n"); } -static int python_start_script_unsupported(const char *script __unused, - int argc __unused, - const char **argv __unused) +static int python_start_script_unsupported(const char *script __maybe_unused, + int argc __maybe_unused, + const char **argv __maybe_unused) { print_python_unsupported_msg(); return -1; } -static int python_generate_script_unsupported(struct pevent *pevent __unused, - const char *outfile __unused) +static int python_generate_script_unsupported(struct pevent *pevent + __maybe_unused, + const char *outfile + __maybe_unused) { print_python_unsupported_msg(); @@ -115,17 +116,18 @@ static void print_perl_unsupported_msg(void) "\n etc.\n"); } -static int perl_start_script_unsupported(const char *script __unused, - int argc __unused, - const char **argv __unused) +static int perl_start_script_unsupported(const char *script __maybe_unused, + int argc __maybe_unused, + const char **argv __maybe_unused) { print_perl_unsupported_msg(); return -1; } -static int perl_generate_script_unsupported(struct pevent *pevent __unused, - const char *outfile __unused) +static int perl_generate_script_unsupported(struct pevent *pevent + __maybe_unused, + const char *outfile __maybe_unused) { print_perl_unsupported_msg(); diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 8fef1d6687b7..a55fd37ffea1 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -9,7 +9,6 @@ struct machine; struct perf_sample; union perf_event; struct perf_tool; -struct thread; extern int header_page_size_size; extern int header_page_ts_size; @@ -32,6 +31,8 @@ int bigendian(void); struct pevent *read_trace_init(int file_bigendian, int host_bigendian); void print_trace_event(struct pevent *pevent, int cpu, void *data, int size); +void event_format__print(struct event_format *event, + int cpu, void *data, int size); void print_event(struct pevent *pevent, int cpu, void *data, int size, unsigned long long nsecs, char *comm); @@ -56,7 +57,7 @@ int trace_parse_common_pid(struct pevent *pevent, void *data); struct event_format *trace_find_next_event(struct pevent *pevent, struct event_format *event); -unsigned long long read_size(struct pevent *pevent, void *ptr, int size); +unsigned long long read_size(struct event_format *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); struct pevent_record *trace_read_data(struct pevent *pevent, int cpu); @@ -74,16 +75,19 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, void tracing_data_put(struct tracing_data *tdata); +struct addr_location; + +struct perf_session; + struct scripting_ops { const char *name; int (*start_script) (const char *script, int argc, const char **argv); int (*stop_script) (void); void (*process_event) (union perf_event *event, - struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct thread *thread); + struct addr_location *al); int (*generate_script) (struct pevent *pevent, const char *outfile); }; diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c new file mode 100644 index 000000000000..958723ba3d2e --- /dev/null +++ b/tools/perf/util/unwind.c @@ -0,0 +1,571 @@ +/* + * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps. + * + * Lots of this code have been borrowed or heavily inspired from parts of + * the libunwind 0.99 code which are (amongst other contributors I may have + * forgotten): + * + * Copyright (C) 2002-2007 Hewlett-Packard Co + * Contributed by David Mosberger-Tang <davidm@hpl.hp.com> + * + * And the bugs have been added by: + * + * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com> + * + */ + +#include <elf.h> +#include <gelf.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <linux/list.h> +#include <libunwind.h> +#include <libunwind-ptrace.h> +#include "thread.h" +#include "session.h" +#include "perf_regs.h" +#include "unwind.h" +#include "util.h" + +extern int +UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ +#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ + +/* Pointer-encoding formats: */ +#define DW_EH_PE_omit 0xff +#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */ +#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */ +#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */ +#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */ +#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */ + +/* Pointer-encoding application: */ +#define DW_EH_PE_absptr 0x00 /* absolute value */ +#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */ + +/* + * The following are not documented by LSB v1.3, yet they are used by + * GCC, presumably they aren't documented by LSB since they aren't + * used on Linux: + */ +#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */ +#define DW_EH_PE_aligned 0x50 /* aligned pointer */ + +/* Flags intentionaly not handled, since they're not needed: + * #define DW_EH_PE_indirect 0x80 + * #define DW_EH_PE_uleb128 0x01 + * #define DW_EH_PE_udata2 0x02 + * #define DW_EH_PE_sleb128 0x09 + * #define DW_EH_PE_sdata2 0x0a + * #define DW_EH_PE_textrel 0x20 + * #define DW_EH_PE_datarel 0x30 + */ + +struct unwind_info { + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; + u64 sample_uregs; +}; + +#define dw_read(ptr, type, end) ({ \ + type *__p = (type *) ptr; \ + type __v; \ + if ((__p + 1) > (type *) end) \ + return -EINVAL; \ + __v = *__p++; \ + ptr = (typeof(ptr)) __p; \ + __v; \ + }) + +static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val, + u8 encoding) +{ + u8 *cur = *p; + *val = 0; + + switch (encoding) { + case DW_EH_PE_omit: + *val = 0; + goto out; + case DW_EH_PE_ptr: + *val = dw_read(cur, unsigned long, end); + goto out; + default: + break; + } + + switch (encoding & DW_EH_PE_APPL_MASK) { + case DW_EH_PE_absptr: + break; + case DW_EH_PE_pcrel: + *val = (unsigned long) cur; + break; + default: + return -EINVAL; + } + + if ((encoding & 0x07) == 0x00) + encoding |= DW_EH_PE_udata4; + + switch (encoding & DW_EH_PE_FORMAT_MASK) { + case DW_EH_PE_sdata4: + *val += dw_read(cur, s32, end); + break; + case DW_EH_PE_udata4: + *val += dw_read(cur, u32, end); + break; + case DW_EH_PE_sdata8: + *val += dw_read(cur, s64, end); + break; + case DW_EH_PE_udata8: + *val += dw_read(cur, u64, end); + break; + default: + return -EINVAL; + } + + out: + *p = cur; + return 0; +} + +#define dw_read_encoded_value(ptr, end, enc) ({ \ + u64 __v; \ + if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \ + return -EINVAL; \ + } \ + __v; \ + }) + +static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name) +{ + Elf_Scn *sec = NULL; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *str; + + gelf_getshdr(sec, shp); + str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); + if (!strcmp(name, str)) + break; + } + + return sec; +} + +static u64 elf_section_offset(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + u64 offset = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + + do { + if (gelf_getehdr(elf, &ehdr) == NULL) + break; + + if (!elf_section_by_name(elf, &ehdr, &shdr, name)) + break; + + offset = shdr.sh_offset; + } while (0); + + elf_end(elf); + return offset; +} + +struct table_entry { + u32 start_ip_offset; + u32 fde_offset; +}; + +struct eh_frame_hdr { + unsigned char version; + unsigned char eh_frame_ptr_enc; + unsigned char fde_count_enc; + unsigned char table_enc; + + /* + * The rest of the header is variable-length and consists of the + * following members: + * + * encoded_t eh_frame_ptr; + * encoded_t fde_count; + */ + + /* A single encoded pointer should not be more than 8 bytes. */ + u64 enc[2]; + + /* + * struct { + * encoded_t start_ip; + * encoded_t fde_addr; + * } binary_search_table[fde_count]; + */ + char data[0]; +} __packed; + +static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, + u64 offset, u64 *table_data, u64 *segbase, + u64 *fde_count) +{ + struct eh_frame_hdr hdr; + u8 *enc = (u8 *) &hdr.enc; + u8 *end = (u8 *) &hdr.data; + ssize_t r; + + r = dso__data_read_offset(dso, machine, offset, + (u8 *) &hdr, sizeof(hdr)); + if (r != sizeof(hdr)) + return -EINVAL; + + /* We dont need eh_frame_ptr, just skip it. */ + dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc); + + *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc); + *segbase = offset; + *table_data = (enc - (u8 *) &hdr) + offset; + return 0; +} + +static int read_unwind_spec(struct dso *dso, struct machine *machine, + u64 *table_data, u64 *segbase, u64 *fde_count) +{ + int ret = -EINVAL, fd; + u64 offset; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; + + offset = elf_section_offset(fd, ".eh_frame_hdr"); + close(fd); + + if (offset) + ret = unwind_spec_ehframe(dso, machine, offset, + table_data, segbase, + fde_count); + + /* TODO .debug_frame check if eh_frame_hdr fails */ + return ret; +} + +static struct map *find_map(unw_word_t ip, struct unwind_info *ui) +{ + struct addr_location al; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + return al.map; +} + +static int +find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, + int need_unwind_info, void *arg) +{ + struct unwind_info *ui = arg; + struct map *map; + unw_dyn_info_t di; + u64 table_data, segbase, fde_count; + + map = find_map(ip, ui); + if (!map || !map->dso) + return -EINVAL; + + pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); + + if (read_unwind_spec(map->dso, ui->machine, + &table_data, &segbase, &fde_count)) + return -EINVAL; + + memset(&di, 0, sizeof(di)); + di.format = UNW_INFO_FORMAT_REMOTE_TABLE; + di.start_ip = map->start; + di.end_ip = map->end; + di.u.rti.segbase = map->start + segbase; + di.u.rti.table_data = map->start + table_data; + di.u.rti.table_len = fde_count * sizeof(struct table_entry) + / sizeof(unw_word_t); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); +} + +static int access_fpreg(unw_addr_space_t __maybe_unused as, + unw_regnum_t __maybe_unused num, + unw_fpreg_t __maybe_unused *val, + int __maybe_unused __write, + void __maybe_unused *arg) +{ + pr_err("unwind: access_fpreg unsupported\n"); + return -UNW_EINVAL; +} + +static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused *dil_addr, + void __maybe_unused *arg) +{ + return -UNW_ENOINFO; +} + +static int resume(unw_addr_space_t __maybe_unused as, + unw_cursor_t __maybe_unused *cu, + void __maybe_unused *arg) +{ + pr_err("unwind: resume unsupported\n"); + return -UNW_EINVAL; +} + +static int +get_proc_name(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused addr, + char __maybe_unused *bufp, size_t __maybe_unused buf_len, + unw_word_t __maybe_unused *offp, void __maybe_unused *arg) +{ + pr_err("unwind: get_proc_name unsupported\n"); + return -UNW_EINVAL; +} + +static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, + unw_word_t *data) +{ + struct addr_location al; + ssize_t size; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, addr, &al); + if (!al.map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!al.map->dso) + return -1; + + size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id, + u64 sample_regs) +{ + int i, idx = 0; + + if (!(sample_regs & (1 << id))) + return -EINVAL; + + for (i = 0; i < id; i++) { + if (sample_regs & (1 << i)) + idx++; + } + + *valp = regs->regs[idx]; + return 0; +} + +static int access_mem(unw_addr_space_t __maybe_unused as, + unw_word_t addr, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + unw_word_t start, end; + int offset; + int ret; + + /* Don't support write, probably not needed. */ + if (__write || !stack || !ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP, + ui->sample_uregs); + if (ret) + return ret; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(unw_word_t) < addr) + return -EINVAL; + + if (addr < start || addr + sizeof(unw_word_t) >= end) { + ret = access_dso_mem(ui, addr, valp); + if (ret) { + pr_debug("unwind: access_mem %p not inside range %p-%p\n", + (void *)addr, (void *)start, (void *)end); + *valp = 0; + return ret; + } + return 0; + } + + offset = addr - start; + *valp = *(unw_word_t *)&stack->data[offset]; + pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n", + (void *)addr, (unsigned long)*valp, offset); + return 0; +} + +static int access_reg(unw_addr_space_t __maybe_unused as, + unw_regnum_t regnum, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + int id, ret; + + /* Don't support write, I suspect we don't need it. */ + if (__write) { + pr_err("unwind: access_reg w %d\n", regnum); + return 0; + } + + if (!ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + id = unwind__arch_reg_id(regnum); + if (id < 0) + return -EINVAL; + + ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs); + if (ret) { + pr_err("unwind: can't read reg %d\n", regnum); + return ret; + } + + pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); + return 0; +} + +static void put_unwind_info(unw_addr_space_t __maybe_unused as, + unw_proc_info_t *pi __maybe_unused, + void *arg __maybe_unused) +{ + pr_debug("unwind: put_unwind_info called\n"); +} + +static int entry(u64 ip, struct thread *thread, struct machine *machine, + unwind_entry_cb_t cb, void *arg) +{ + struct unwind_entry e; + struct addr_location al; + + thread__find_addr_location(thread, machine, + PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al, NULL); + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return cb(&e, arg); +} + +static void display_error(int err) +{ + switch (err) { + case UNW_EINVAL: + pr_err("unwind: Only supports local.\n"); + break; + case UNW_EUNSPEC: + pr_err("unwind: Unspecified error.\n"); + break; + case UNW_EBADREG: + pr_err("unwind: Register unavailable.\n"); + break; + default: + break; + } +} + +static unw_accessors_t accessors = { + .find_proc_info = find_proc_info, + .put_unwind_info = put_unwind_info, + .get_dyn_info_list_addr = get_dyn_info_list_addr, + .access_mem = access_mem, + .access_reg = access_reg, + .access_fpreg = access_fpreg, + .resume = resume, + .get_proc_name = get_proc_name, +}; + +static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, + void *arg) +{ + unw_addr_space_t addr_space; + unw_cursor_t c; + int ret; + + addr_space = unw_create_addr_space(&accessors, 0); + if (!addr_space) { + pr_err("unwind: Can't create unwind address space.\n"); + return -ENOMEM; + } + + ret = unw_init_remote(&c, addr_space, ui); + if (ret) + display_error(ret); + + while (!ret && (unw_step(&c) > 0)) { + unw_word_t ip; + + unw_get_reg(&c, UNW_REG_IP, &ip); + ret = entry(ip, ui->thread, ui->machine, cb, arg); + } + + unw_destroy_addr_space(addr_space); + return ret; +} + +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, struct thread *thread, + u64 sample_uregs, struct perf_sample *data) +{ + unw_word_t ip; + struct unwind_info ui = { + .sample = data, + .sample_uregs = sample_uregs, + .thread = thread, + .machine = machine, + }; + int ret; + + if (!data->user_regs.regs) + return -EINVAL; + + ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs); + if (ret) + return ret; + + ret = entry(ip, thread, machine, cb, arg); + if (ret) + return -ENOMEM; + + return get_entries(&ui, cb, arg); +} diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h new file mode 100644 index 000000000000..a78c8b303bb5 --- /dev/null +++ b/tools/perf/util/unwind.h @@ -0,0 +1,35 @@ +#ifndef __UNWIND_H +#define __UNWIND_H + +#include "types.h" +#include "event.h" +#include "symbol.h" + +struct unwind_entry { + struct map *map; + struct symbol *sym; + u64 ip; +}; + +typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); + +#ifndef NO_LIBUNWIND_SUPPORT +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, + struct thread *thread, + u64 sample_uregs, + struct perf_sample *data); +int unwind__arch_reg_id(int regnum); +#else +static inline int +unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, + void *arg __maybe_unused, + struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + u64 sample_uregs __maybe_unused, + struct perf_sample *data __maybe_unused) +{ + return 0; +} +#endif /* NO_LIBUNWIND_SUPPORT */ +#endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index d03599fbe78b..2055cf38041c 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,6 +1,11 @@ #include "../perf.h" #include "util.h" #include <sys/mman.h> +#ifndef NO_BACKTRACE +#include <execinfo.h> +#endif +#include <stdio.h> +#include <stdlib.h> /* * XXX We need to find a better place for these things... @@ -158,3 +163,23 @@ size_t hex_width(u64 v) return n; } + +/* Obtain a backtrace and print it to stdout. */ +#ifndef NO_BACKTRACE +void dump_stack(void) +{ + void *array[16]; + size_t size = backtrace(array, ARRAY_SIZE(array)); + char **strings = backtrace_symbols(array, size); + size_t i; + + printf("Obtained %zd stack frames.\n", size); + + for (i = 0; i < size; i++) + printf("%s\n", strings[i]); + + free(strings); +} +#else +void dump_stack(void) {} +#endif diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b13c7331eaf8..70fa70b535b2 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -69,13 +69,8 @@ #include <sys/poll.h> #include <sys/socket.h> #include <sys/ioctl.h> -#include <sys/select.h> -#include <netinet/in.h> -#include <netinet/tcp.h> -#include <arpa/inet.h> -#include <netdb.h> #include <inttypes.h> -#include "../../../include/linux/magic.h" +#include <linux/magic.h> #include "types.h" #include <sys/ttydefaults.h> @@ -266,4 +261,6 @@ size_t hex_width(u64 v); char *rtrim(char *s); +void dump_stack(void); + #endif diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c new file mode 100644 index 000000000000..e60951fcdb12 --- /dev/null +++ b/tools/perf/util/vdso.c @@ -0,0 +1,111 @@ + +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdlib.h> +#include <linux/kernel.h> + +#include "vdso.h" +#include "util.h" +#include "symbol.h" +#include "linux/string.h" + +static bool vdso_found; +static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX"; + +static int find_vdso_map(void **start, void **end) +{ + FILE *maps; + char line[128]; + int found = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + pr_err("vdso: cannot open maps\n"); + return -1; + } + + while (!found && fgets(line, sizeof(line), maps)) { + int m = -1; + + /* We care only about private r-x mappings. */ + if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", + start, end, &m)) + continue; + if (m < 0) + continue; + + if (!strncmp(&line[m], VDSO__MAP_NAME, + sizeof(VDSO__MAP_NAME) - 1)) + found = 1; + } + + fclose(maps); + return !found; +} + +static char *get_file(void) +{ + char *vdso = NULL; + char *buf = NULL; + void *start, *end; + size_t size; + int fd; + + if (vdso_found) + return vdso_file; + + if (find_vdso_map(&start, &end)) + return NULL; + + size = end - start; + + buf = memdup(start, size); + if (!buf) + return NULL; + + fd = mkstemp(vdso_file); + if (fd < 0) + goto out; + + if (size == (size_t) write(fd, buf, size)) + vdso = vdso_file; + + close(fd); + + out: + free(buf); + + vdso_found = (vdso != NULL); + return vdso; +} + +void vdso__exit(void) +{ + if (vdso_found) + unlink(vdso_file); +} + +struct dso *vdso__dso_findnew(struct list_head *head) +{ + struct dso *dso = dsos__find(head, VDSO__MAP_NAME); + + if (!dso) { + char *file; + + file = get_file(); + if (!file) + return NULL; + + dso = dso__new(VDSO__MAP_NAME); + if (dso != NULL) { + dsos__add(head, dso); + dso__set_long_name(dso, file); + } + } + + return dso; +} diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h new file mode 100644 index 000000000000..0f76e7caf6f8 --- /dev/null +++ b/tools/perf/util/vdso.h @@ -0,0 +1,18 @@ +#ifndef __PERF_VDSO__ +#define __PERF_VDSO__ + +#include <linux/types.h> +#include <string.h> +#include <stdbool.h> + +#define VDSO__MAP_NAME "[vdso]" + +static inline bool is_vdso_map(const char *filename) +{ + return !strcmp(filename, VDSO__MAP_NAME); +} + +struct dso *vdso__dso_findnew(struct list_head *head); +void vdso__exit(void); + +#endif /* __PERF_VDSO__ */ diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c index 73e900edb5a2..19f15b650703 100644 --- a/tools/perf/util/wrapper.c +++ b/tools/perf/util/wrapper.c @@ -7,7 +7,8 @@ * There's no pack memory to release - but stay close to the Git * version so wrap this away: */ -static inline void release_pack_memory(size_t size __used, int flag __used) +static inline void release_pack_memory(size_t size __maybe_unused, + int flag __maybe_unused) { } diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index bde8521d56bb..96ce80a3743b 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -1,6 +1,8 @@ ifeq ("$(origin O)", "command line") - OUTPUT := $(O)/ - COMMAND_O := O=$(O) + dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),) + ABSOLUTE_O := $(shell cd $(O) ; pwd) + OUTPUT := $(ABSOLUTE_O)/ + COMMAND_O := O=$(ABSOLUTE_O) endif ifneq ($(OUTPUT),) |