| Message ID | 20240708032847.2998158-3-ruanjinjie@huawei.com (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 1a7483318274d0ec60f160e604c2a1dbce27fc0a |
| Headers | show |
| Series | riscv: stacktrace: Add USER_STACKTRACE support | expand |
On 2024/7/8 11:28, Jinjie Ruan wrote: > Currently, userstacktrace is unsupported for riscv. So use the > perf_callchain_user() code as blueprint to implement the > arch_stack_walk_user() which add userstacktrace support on riscv. > Meanwhile, we can use arch_stack_walk_user() to simplify the implementation > of perf_callchain_user(). > > A ftrace test case is shown as below: > > # cd /sys/kernel/debug/tracing > # echo 1 > options/userstacktrace > # echo 1 > options/sym-userobj > # echo 1 > events/sched/sched_process_fork/enable > # cat trace > ...... > bash-178 [000] ...1. 97.968395: sched_process_fork: comm=bash pid=178 child_comm=bash child_pid=231 > bash-178 [000] ...1. 97.970075: <user stack trace> > => /lib/libc.so.6[+0xb5090] > > Also a simple perf test is ok as below: > > # perf record -e cpu-clock --call-graph fp top > # perf report --call-graph > > ..... > [[31m 66.54%[[m 0.00% top [kernel.kallsyms] [k] ret_from_exception > | > ---ret_from_exception > | > |--[[31m58.97%[[m--do_trap_ecall_u > | | > | |--[[31m17.34%[[m--__riscv_sys_read > | | ksys_read > | | | > | | --[[31m16.88%[[m--vfs_read > | | | > | | |--[[31m10.90%[[m--seq_read Gentle ping. > > Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> > Tested-by: Jinjie Ruan <ruanjinjie@huawei.com> > Cc: Björn Töpel <bjorn@kernel.org> > --- > v3: > - Remove the LTP message as Björn suggested. > - Keep fp 16-bytes aligned in arch_stack_walk_user(). > - Add the test info. > v2: > - Fix the cocci warning, !A || A && B is equivalent to !A || B. > --- > --- > arch/riscv/Kconfig | 1 + > arch/riscv/kernel/perf_callchain.c | 46 ++---------------------------- > arch/riscv/kernel/stacktrace.c | 43 ++++++++++++++++++++++++++++ > 3 files changed, 47 insertions(+), 43 deletions(-) > > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig > index 3b44e7b51436..46121dbcf750 100644 > --- a/arch/riscv/Kconfig > +++ b/arch/riscv/Kconfig > @@ -194,6 +194,7 @@ config RISCV > select THREAD_INFO_IN_TASK > select TRACE_IRQFLAGS_SUPPORT > select UACCESS_MEMCPY if !MMU > + select USER_STACKTRACE_SUPPORT > select ZONE_DMA32 if 64BIT > > config CLANG_SUPPORTS_DYNAMIC_FTRACE > diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c > index 2932791e9388..c7468af77c66 100644 > --- a/arch/riscv/kernel/perf_callchain.c > +++ b/arch/riscv/kernel/perf_callchain.c > @@ -6,37 +6,9 @@ > > #include <asm/stacktrace.h> > > -/* > - * Get the return address for a single stackframe and return a pointer to the > - * next frame tail. > - */ > -static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, > - unsigned long fp, unsigned long reg_ra) > +static bool fill_callchain(void *entry, unsigned long pc) > { > - struct stackframe buftail; > - unsigned long ra = 0; > - unsigned long __user *user_frame_tail = > - (unsigned long __user *)(fp - sizeof(struct stackframe)); > - > - /* Check accessibility of one struct frame_tail beyond */ > - if (!access_ok(user_frame_tail, sizeof(buftail))) > - return 0; > - if (__copy_from_user_inatomic(&buftail, user_frame_tail, > - sizeof(buftail))) > - return 0; > - > - if (reg_ra != 0) > - ra = reg_ra; > - else > - ra = buftail.ra; > - > - fp = buftail.fp; > - if (ra != 0) > - perf_callchain_store(entry, ra); > - else > - return 0; > - > - return fp; > + return perf_callchain_store(entry, pc) == 0; > } > > /* > @@ -56,19 +28,7 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, > void perf_callchain_user(struct perf_callchain_entry_ctx *entry, > struct pt_regs *regs) > { > - unsigned long fp = 0; > - > - fp = regs->s0; > - perf_callchain_store(entry, regs->epc); > - > - fp = user_backtrace(entry, fp, regs->ra); > - while (fp && !(fp & 0x7) && entry->nr < entry->max_stack) > - fp = user_backtrace(entry, fp, 0); > -} > - > -static bool fill_callchain(void *entry, unsigned long pc) > -{ > - return perf_callchain_store(entry, pc) == 0; > + arch_stack_walk_user(fill_callchain, entry, regs); > } > > void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, > diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c > index 0d3f00eb0bae..5480cc11b523 100644 > --- a/arch/riscv/kernel/stacktrace.c > +++ b/arch/riscv/kernel/stacktrace.c > @@ -161,3 +161,46 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void > { > walk_stackframe(task, regs, consume_entry, cookie); > } > + > +/* > + * Get the return address for a single stackframe and return a pointer to the > + * next frame tail. > + */ > +static unsigned long unwind_user_frame(stack_trace_consume_fn consume_entry, > + void *cookie, unsigned long fp, > + unsigned long reg_ra) > +{ > + struct stackframe buftail; > + unsigned long ra = 0; > + unsigned long __user *user_frame_tail = > + (unsigned long __user *)(fp - sizeof(struct stackframe)); > + > + /* Check accessibility of one struct frame_tail beyond */ > + if (!access_ok(user_frame_tail, sizeof(buftail))) > + return 0; > + if (__copy_from_user_inatomic(&buftail, user_frame_tail, > + sizeof(buftail))) > + return 0; > + > + ra = reg_ra ? : buftail.ra; > + > + fp = buftail.fp; > + if (!ra || !consume_entry(cookie, ra)) > + return 0; > + > + return fp; > +} > + > +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, > + const struct pt_regs *regs) > +{ > + unsigned long fp = 0; > + > + fp = regs->s0; > + if (!consume_entry(cookie, regs->epc)) > + return; > + > + fp = unwind_user_frame(consume_entry, cookie, fp, regs->ra); > + while (fp && !(fp & 0x7)) > + fp = unwind_user_frame(consume_entry, cookie, fp, 0); > +}
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 3b44e7b51436..46121dbcf750 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -194,6 +194,7 @@ config RISCV select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select UACCESS_MEMCPY if !MMU + select USER_STACKTRACE_SUPPORT select ZONE_DMA32 if 64BIT config CLANG_SUPPORTS_DYNAMIC_FTRACE diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 2932791e9388..c7468af77c66 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -6,37 +6,9 @@ #include <asm/stacktrace.h> -/* - * Get the return address for a single stackframe and return a pointer to the - * next frame tail. - */ -static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, - unsigned long fp, unsigned long reg_ra) +static bool fill_callchain(void *entry, unsigned long pc) { - struct stackframe buftail; - unsigned long ra = 0; - unsigned long __user *user_frame_tail = - (unsigned long __user *)(fp - sizeof(struct stackframe)); - - /* Check accessibility of one struct frame_tail beyond */ - if (!access_ok(user_frame_tail, sizeof(buftail))) - return 0; - if (__copy_from_user_inatomic(&buftail, user_frame_tail, - sizeof(buftail))) - return 0; - - if (reg_ra != 0) - ra = reg_ra; - else - ra = buftail.ra; - - fp = buftail.fp; - if (ra != 0) - perf_callchain_store(entry, ra); - else - return 0; - - return fp; + return perf_callchain_store(entry, pc) == 0; } /* @@ -56,19 +28,7 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - unsigned long fp = 0; - - fp = regs->s0; - perf_callchain_store(entry, regs->epc); - - fp = user_backtrace(entry, fp, regs->ra); - while (fp && !(fp & 0x7) && entry->nr < entry->max_stack) - fp = user_backtrace(entry, fp, 0); -} - -static bool fill_callchain(void *entry, unsigned long pc) -{ - return perf_callchain_store(entry, pc) == 0; + arch_stack_walk_user(fill_callchain, entry, regs); } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 0d3f00eb0bae..5480cc11b523 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -161,3 +161,46 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void { walk_stackframe(task, regs, consume_entry, cookie); } + +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static unsigned long unwind_user_frame(stack_trace_consume_fn consume_entry, + void *cookie, unsigned long fp, + unsigned long reg_ra) +{ + struct stackframe buftail; + unsigned long ra = 0; + unsigned long __user *user_frame_tail = + (unsigned long __user *)(fp - sizeof(struct stackframe)); + + /* Check accessibility of one struct frame_tail beyond */ + if (!access_ok(user_frame_tail, sizeof(buftail))) + return 0; + if (__copy_from_user_inatomic(&buftail, user_frame_tail, + sizeof(buftail))) + return 0; + + ra = reg_ra ? : buftail.ra; + + fp = buftail.fp; + if (!ra || !consume_entry(cookie, ra)) + return 0; + + return fp; +} + +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) +{ + unsigned long fp = 0; + + fp = regs->s0; + if (!consume_entry(cookie, regs->epc)) + return; + + fp = unwind_user_frame(consume_entry, cookie, fp, regs->ra); + while (fp && !(fp & 0x7)) + fp = unwind_user_frame(consume_entry, cookie, fp, 0); +}
Currently, userstacktrace is unsupported for riscv. So use the perf_callchain_user() code as blueprint to implement the arch_stack_walk_user() which add userstacktrace support on riscv. Meanwhile, we can use arch_stack_walk_user() to simplify the implementation of perf_callchain_user(). A ftrace test case is shown as below: # cd /sys/kernel/debug/tracing # echo 1 > options/userstacktrace # echo 1 > options/sym-userobj # echo 1 > events/sched/sched_process_fork/enable # cat trace ...... bash-178 [000] ...1. 97.968395: sched_process_fork: comm=bash pid=178 child_comm=bash child_pid=231 bash-178 [000] ...1. 97.970075: <user stack trace> => /lib/libc.so.6[+0xb5090] Also a simple perf test is ok as below: # perf record -e cpu-clock --call-graph fp top # perf report --call-graph ..... [[31m 66.54%[[m 0.00% top [kernel.kallsyms] [k] ret_from_exception | ---ret_from_exception | |--[[31m58.97%[[m--do_trap_ecall_u | | | |--[[31m17.34%[[m--__riscv_sys_read | | ksys_read | | | | | --[[31m16.88%[[m--vfs_read | | | | | |--[[31m10.90%[[m--seq_read Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Tested-by: Jinjie Ruan <ruanjinjie@huawei.com> Cc: Björn Töpel <bjorn@kernel.org> --- v3: - Remove the LTP message as Björn suggested. - Keep fp 16-bytes aligned in arch_stack_walk_user(). - Add the test info. v2: - Fix the cocci warning, !A || A && B is equivalent to !A || B. --- --- arch/riscv/Kconfig | 1 + arch/riscv/kernel/perf_callchain.c | 46 ++---------------------------- arch/riscv/kernel/stacktrace.c | 43 ++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+), 43 deletions(-)