| Message ID | 86d18d80affc39cf9579a24f1beb7c8631cfa9bd.1567060834.git.han_mao@c-sky.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | riscv: Add perf callchain support | expand |
Hello Mao Han, On Thu, 29 Aug 2019, Mao Han wrote: > This patch add support for perf callchain sampling on riscv platform. > The return address of leaf function is retrieved from pt_regs as > it is not saved in the outmost frame. > > Signed-off-by: Mao Han <han_mao@c-sky.com> > Cc: Paul Walmsley <paul.walmsley@sifive.com> > Cc: Greentime Hu <green.hu@gmail.com> > Cc: Palmer Dabbelt <palmer@sifive.com> > Cc: linux-riscv <linux-riscv@lists.infradead.org> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Guo Ren <guoren@kernel.org> There are some 'checkpatch.pl --strict' warnings with this patch (below). These have been fixed here. The following patch has been queued for v5.4-rc1 with Greentime's Tested-by:. Thanks for your hard work following up on the feedback with these patches - - Paul CHECK: Alignment should match open parenthesis #77: FILE: arch/riscv/kernel/perf_callchain.c:18: +static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, + unsigned long fp, unsigned long reg_ra) CHECK: Blank lines aren't necessary after an open brace '{' #146: FILE: arch/riscv/kernel/perf_callchain.c:87: +{ + CHECK: Alignment should match open parenthesis #165: FILE: arch/riscv/kernel/stacktrace.c:23: +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) ------ From: Mao Han <han_mao@c-sky.com> Date: Thu, 29 Aug 2019 14:57:00 +0800 Subject: [PATCH] riscv: Add perf callchain support This patch adds support for perf callchain sampling on riscv platforms. The return address of leaf function is retrieved from pt_regs as it is not saved in the outmost frame. Signed-off-by: Mao Han <han_mao@c-sky.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: linux-riscv <linux-riscv@lists.infradead.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Guo Ren <guoren@kernel.org> Tested-by: Greentime Hu <greentime.hu@sifive.com> [paul.walmsley@sifive.com: fixed some 'checkpatch.pl --strict' issues; fixed patch description spelling] Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com> --- arch/riscv/Makefile | 3 + arch/riscv/kernel/Makefile | 3 +- arch/riscv/kernel/perf_callchain.c | 94 ++++++++++++++++++++++++++++++ arch/riscv/kernel/stacktrace.c | 4 +- 4 files changed, 101 insertions(+), 3 deletions(-) create mode 100644 arch/riscv/kernel/perf_callchain.c diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index a73659e30f8d..4f0a3d2018d2 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -54,6 +54,9 @@ endif ifeq ($(CONFIG_MODULE_SECTIONS),y) KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds endif +ifeq ($(CONFIG_PERF_EVENTS),y) + KBUILD_CFLAGS += -fno-omit-frame-pointer +endif KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 2420d37d96de..b1bea89fc814 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o clean: diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c new file mode 100644 index 000000000000..8d2804f05cf9 --- /dev/null +++ b/arch/riscv/kernel/perf_callchain.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ + +#include <linux/perf_event.h> +#include <linux/uaccess.h> + +/* Kernel callchain */ +struct stackframe { + unsigned long fp; + unsigned long ra; +}; + +/* + * 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) +{ + struct stackframe buftail; + unsigned long ra = 0; + unsigned long *user_frame_tail = + (unsigned long *)(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; +} + +/* + * This will be called when the target is in user mode + * This function will only be called when we use + * "PERF_SAMPLE_CALLCHAIN" in + * kernel/events/core.c:perf_prepare_sample() + * + * How to trigger perf_callchain_[user/kernel] : + * $ perf record -e cpu-clock --call-graph fp ./program + * $ perf report --call-graph + * + * On RISC-V platform, the program being sampled and the C library + * need to be compiled with -fno-omit-frame-pointer, otherwise + * the user stack will not contain function frame. + */ +void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + unsigned long fp = 0; + + /* RISC-V does not support perf in guest mode. */ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + return; + + fp = regs->s0; + perf_callchain_store(entry, regs->sepc); + + fp = user_backtrace(entry, fp, regs->ra); + while (fp && !(fp & 0x3) && entry->nr < entry->max_stack) + fp = user_backtrace(entry, fp, 0); +} + +bool fill_callchain(unsigned long pc, void *entry) +{ + return perf_callchain_store(entry, pc); +} + +void notrace walk_stackframe(struct task_struct *task, + struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg); +void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + /* RISC-V does not support perf in guest mode. */ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + pr_warn("RISC-V does not support perf in guest mode!"); + return; + } + + walk_stackframe(NULL, regs, fill_callchain, entry); +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index f15642715d1a..0940681d2f68 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -19,8 +19,8 @@ struct stackframe { unsigned long ra; }; -static void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, + bool (*fn)(unsigned long, void *), void *arg) { unsigned long fp, sp, pc;
On Wed, Sep 04, 2019 at 12:54:41PM -0700, Paul Walmsley wrote: > Hello Mao Han, > > On Thu, 29 Aug 2019, Mao Han wrote: > > > This patch add support for perf callchain sampling on riscv platform. > > The return address of leaf function is retrieved from pt_regs as > > it is not saved in the outmost frame. > > > > Signed-off-by: Mao Han <han_mao@c-sky.com> > > Cc: Paul Walmsley <paul.walmsley@sifive.com> > > Cc: Greentime Hu <green.hu@gmail.com> > > Cc: Palmer Dabbelt <palmer@sifive.com> > > Cc: linux-riscv <linux-riscv@lists.infradead.org> > > Cc: Christoph Hellwig <hch@lst.de> > > Cc: Guo Ren <guoren@kernel.org> > > There are some 'checkpatch.pl --strict' warnings with this patch (below). > These have been fixed here. The following patch has been queued for > v5.4-rc1 with Greentime's Tested-by:. Thanks for your hard work following > up on the feedback with these patches - Thanks for the fixes. I'll check patches with --strict next time. Thanks, Mao Han
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 7a117be..946565b 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -54,6 +54,9 @@ endif ifeq ($(CONFIG_MODULE_SECTIONS),y) KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/riscv/kernel/module.lds endif +ifeq ($(CONFIG_PERF_EVENTS),y) + KBUILD_CFLAGS += -fno-omit-frame-pointer +endif KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 2420d37..b1bea89 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o clean: diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c new file mode 100644 index 0000000..72168e1 --- /dev/null +++ b/arch/riscv/kernel/perf_callchain.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ + +#include <linux/perf_event.h> +#include <linux/uaccess.h> + +/* Kernel callchain */ +struct stackframe { + unsigned long fp; + unsigned long ra; +}; + +/* + * 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) +{ + struct stackframe buftail; + unsigned long ra = 0; + unsigned long *user_frame_tail = + (unsigned long *)(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; +} + +/* + * This will be called when the target is in user mode + * This function will only be called when we use + * "PERF_SAMPLE_CALLCHAIN" in + * kernel/events/core.c:perf_prepare_sample() + * + * How to trigger perf_callchain_[user/kernel] : + * $ perf record -e cpu-clock --call-graph fp ./program + * $ perf report --call-graph + * + * On RISC-V platform, the program being sampled and the C library + * need to be compiled with -fno-omit-frame-pointer, otherwise + * the user stack will not contain function frame. + */ +void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + unsigned long fp = 0; + + /* RISC-V does not support perf in guest mode. */ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + return; + + fp = regs->s0; + perf_callchain_store(entry, regs->sepc); + + fp = user_backtrace(entry, fp, regs->ra); + while (fp && !(fp & 0x3) && entry->nr < entry->max_stack) + fp = user_backtrace(entry, fp, 0); +} + +bool fill_callchain(unsigned long pc, void *entry) +{ + return perf_callchain_store(entry, pc); +} + +void notrace walk_stackframe(struct task_struct *task, + struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg); +void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + + /* RISC-V does not support perf in guest mode. */ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + pr_warn("RISC-V does not support perf in guest mode!"); + return; + } + + walk_stackframe(NULL, regs, fill_callchain, entry); +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index f156427..9b376c1 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -19,7 +19,7 @@ struct stackframe { unsigned long ra; }; -static void notrace walk_stackframe(struct task_struct *task, +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { unsigned long fp, sp, pc;
This patch add support for perf callchain sampling on riscv platform. The return address of leaf function is retrieved from pt_regs as it is not saved in the outmost frame. Signed-off-by: Mao Han <han_mao@c-sky.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: linux-riscv <linux-riscv@lists.infradead.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Guo Ren <guoren@kernel.org> --- arch/riscv/Makefile | 3 ++ arch/riscv/kernel/Makefile | 3 +- arch/riscv/kernel/perf_callchain.c | 95 ++++++++++++++++++++++++++++++++++++++ arch/riscv/kernel/stacktrace.c | 2 +- 4 files changed, 101 insertions(+), 2 deletions(-) create mode 100644 arch/riscv/kernel/perf_callchain.c