Re: [PATCH v5] perf machine: arm/arm64: Improve completeness for kernel address space

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 15/08/19 11:25 AM, Leo Yan wrote:
> Arm and arm64 architecture reserve some memory regions prior to the
> symbol '_stext' and these memory regions later will be used by device
> module and BPF jit.  The current code misses to consider these memory
> regions thus any address in the regions will be taken as user space
> mode, but perf cannot find the corresponding dso with the wrong CPU
> mode so we misses to generate samples for device module and BPF
> related trace data.
> 
> This patch parse the link scripts to get the memory size prior to start
> address and reduce this size from 'machine>->kernel_start', then can
> get a fixed up kernel start address which contain memory regions for
> device module and BPF.  Finally, machine__get_kernel_start() can reflect
> more complete kernel memory regions and perf can successfully generate
> samples.
> 
> The reason for parsing the link scripts is Arm architecture changes text
> offset dependent on different platforms, which define multiple text
> offsets in $kernel/arch/arm/Makefile.  This offset is decided when build
> kernel and the final value is extended in the link script, so we can
> extract the used value from the link script.  We use the same way to
> parse arm64 link script as well.  If fail to find the link script, the
> pre start memory size is assumed as zero, in this case it has no any
> change caused with this patch.
> 
> Below is detailed info for testing this patch:
> 
> - Install or build LLVM/Clang;
> 
> - Configure perf with ~/.perfconfig:
> 
>   root@debian:~# cat ~/.perfconfig
>   # this file is auto-generated.
>   [llvm]
>           clang-path = /mnt/build/llvm-build/build/install/bin/clang
>           kbuild-dir = /mnt/linux-kernel/linux-cs-dev/
>           clang-opt = "-g"
>           dump-obj = true
> 
>   [trace]
>           show_zeros = yes
>           show_duration = no
>           no_inherit = yes
>           show_timestamp = no
>           show_arg_names = no
>           args_alignment = 40
>           show_prefix = yes
> 
> - Run 'perf trace' command with eBPF event:
> 
>   root@debian:~# perf trace -e string \
>       -e $kernel/tools/perf/examples/bpf/augmented_raw_syscalls.c
> 
> - Read eBPF program memory mapping in kernel:
> 
>   root@debian:~# echo 1 > /proc/sys/net/core/bpf_jit_kallsyms
>   root@debian:~# cat /proc/kallsyms | grep -E "bpf_prog_.+_sys_[enter|exit]"
>   ffff00000008a0d0 t bpf_prog_e470211b846088d5_sys_enter  [bpf]
>   ffff00000008c6a4 t bpf_prog_29c7ae234d79bd5c_sys_exit   [bpf]
> 
> - Launch any program which accesses file system frequently so can hit
>   the system calls trace flow with eBPF event;
> 
> - Capture CoreSight trace data with filtering eBPF program:
> 
>   root@debian:~# perf record -e cs_etm/@tmc_etr0/ \
> 	--filter 'filter 0xffff00000008a0d0/0x800' -a sleep 5s
> 
> - Decode the eBPF program symbol 'bpf_prog_f173133dc38ccf87_sys_enter':
> 
>   root@debian:~# perf script -F,ip,sym
>   Frame deformatter: Found 4 FSYNCS
>                   0 [unknown]
>    ffff00000008a1ac bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a250 bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a124 bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a14c bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a13c bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a14c bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a180 bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a1ac bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a190 bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a1ac bpf_prog_e470211b846088d5_sys_enter
>    ffff00000008a250 bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a124 bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a14c bpf_prog_e470211b846088d5_sys_enter
>                   0 [unknown]
>    ffff00000008a180 bpf_prog_e470211b846088d5_sys_enter
>    [...]
> 
> Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
> Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
> Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
> Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Suzuki Poulouse <suzuki.poulose@xxxxxxx>
> Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
> Cc: coresight@xxxxxxxxxxxxxxxx
> Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
> Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
> ---
>  tools/perf/Makefile.config | 22 ++++++++++++++++++++++
>  tools/perf/util/machine.c  | 15 ++++++++++++++-
>  2 files changed, 36 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
> index e4988f49ea79..d7ff839d8b20 100644
> --- a/tools/perf/Makefile.config
> +++ b/tools/perf/Makefile.config
> @@ -48,9 +48,20 @@ ifeq ($(SRCARCH),x86)
>    NO_PERF_REGS := 0
>  endif
>  
> +ARM_PRE_START_SIZE := 0
> +
>  ifeq ($(SRCARCH),arm)
>    NO_PERF_REGS := 0
>    LIBUNWIND_LIBS = -lunwind -lunwind-arm
> +  ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds),)
> +    # Extract info from lds:
> +    #   . = ((0xC0000000)) + 0x00208000;
> +    # ARM_PRE_START_SIZE := 0x00208000
> +    ARM_PRE_START_SIZE := $(shell egrep ' \. \= \({2}0x[0-9a-fA-F]+\){2}' \
> +      $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds | \
> +      sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \
> +      awk -F' ' '{printf "0x%x", $$2}' 2>/dev/null)
> +  endif
>  endif
>  
>  ifeq ($(SRCARCH),arm64)
> @@ -58,8 +69,19 @@ ifeq ($(SRCARCH),arm64)
>    NO_SYSCALL_TABLE := 0
>    CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
>    LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
> +  ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds),)
> +    # Extract info from lds:
> +    #  . = ((((((((0xffffffffffffffff)) - (((1)) << (48)) + 1) + (0)) + (0x08000000))) + (0x08000000))) + 0x00080000;
> +    # ARM_PRE_START_SIZE := (0x08000000 + 0x08000000 + 0x00080000) = 0x10080000
> +    ARM_PRE_START_SIZE := $(shell egrep ' \. \= \({8}0x[0-9a-fA-F]+\){2}' \
> +      $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds | \
> +      sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \
> +      awk -F' ' '{printf "0x%x", $$6+$$7+$$8}' 2>/dev/null)
> +  endif

So, that is not going to work if you take a perf.data file to a non-arm machine?

How come you cannot use kallsyms to get the information?

>  endif
>  
> +CFLAGS += -DARM_PRE_START_SIZE=$(ARM_PRE_START_SIZE)
> +
>  ifeq ($(SRCARCH),csky)
>    NO_PERF_REGS := 0
>  endif
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index f6ee7fbad3e4..e993f891bb82 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -2687,13 +2687,26 @@ int machine__get_kernel_start(struct machine *machine)
>  	machine->kernel_start = 1ULL << 63;
>  	if (map) {
>  		err = map__load(map);
> +		if (err)
> +			return err;
> +
>  		/*
>  		 * On x86_64, PTI entry trampolines are less than the
>  		 * start of kernel text, but still above 2^63. So leave
>  		 * kernel_start = 1ULL << 63 for x86_64.
>  		 */
> -		if (!err && !machine__is(machine, "x86_64"))
> +		if (!machine__is(machine, "x86_64"))
>  			machine->kernel_start = map->start;
> +
> +		/*
> +		 * On arm/arm64, the kernel uses some memory regions which are
> +		 * prior to '_stext' symbol; to reflect the complete kernel
> +		 * address space, compensate these pre-defined regions for
> +		 * kernel start address.
> +		 */
> +		if (!strcmp(perf_env__arch(machine->env), "arm") ||
> +		    !strcmp(perf_env__arch(machine->env), "arm64"))
> +			machine->kernel_start -= ARM_PRE_START_SIZE;
>  	}
>  	return err;
>  }
> 




[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux