@@ -51,6 +51,17 @@ endif
ifeq ($(SRCARCH),arm)
NO_PERF_REGS := 0
LIBUNWIND_LIBS = -lunwind -lunwind-arm
+ PRE_START_SIZE := 0
+ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds),)
+ # Extract info from lds:
+ # . = ((0xC0000000)) + 0x00208000;
+ # PRE_START_SIZE := 0x00208000
+ 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
+ CFLAGS += -DARM_PRE_START_SIZE=$(PRE_START_SIZE)
endif
ifeq ($(SRCARCH),arm64)
@@ -58,6 +69,17 @@ ifeq ($(SRCARCH),arm64)
NO_SYSCALL_TABLE := 0
CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
+ PRE_START_SIZE := 0
+ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds),)
+ # Extract info from lds:
+ # . = ((((((((0xffffffffffffffff)) - (((1)) << (48)) + 1) + (0)) + (0x08000000))) + (0x08000000))) + 0x00080000;
+ # PRE_START_SIZE := (0x08000000 + 0x08000000 + 0x00080000) = 0x10080000
+ 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
+ CFLAGS += -DARM_PRE_START_SIZE=$(PRE_START_SIZE)
endif
ifeq ($(SRCARCH),csky)
@@ -1,3 +1,5 @@
+perf-y += machine.o
+
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
new file mode 100644
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+
+void arch__fix_kernel_text_start(u64 *start)
+{
+ /*
+ * On arm, the 16MB virtual memory space prior to 'kernel_start' is
+ * allocated to device modules, a PMD table if CONFIG_HIGHMEM is
+ * enabled and a PGD table. To reflect the complete kernel address
+ * space, compensate the pre-defined regions for kernel start address.
+ */
+ *start = *start - ARM_PRE_START_SIZE;
+}
@@ -1,4 +1,5 @@
perf-y += header.o
+perf-y += machine.o
perf-y += sym-handling.o
perf-$(CONFIG_DWARF) += dwarf-regs.o
perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
new file mode 100644
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+
+void arch__fix_kernel_text_start(u64 *start)
+{
+ /*
+ * On arm64, the root PGD table, device module memory region and
+ * BPF jit region are prior to 'kernel_start'. To reflect the
+ * complete kernel address space, compensate these pre-defined
+ * regions for kernel start address.
+ */
+ *start = *start - ARM_PRE_START_SIZE;
+}
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@linaro.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Leo Yan <leo.yan@linaro.org> --- tools/perf/Makefile.config | 22 ++++++++++++++++++++++ tools/perf/arch/arm/util/Build | 2 ++ tools/perf/arch/arm/util/machine.c | 17 +++++++++++++++++ tools/perf/arch/arm64/util/Build | 1 + tools/perf/arch/arm64/util/machine.c | 17 +++++++++++++++++ 5 files changed, 59 insertions(+) create mode 100644 tools/perf/arch/arm/util/machine.c create mode 100644 tools/perf/arch/arm64/util/machine.c