From 318580ad7f2828f6269e0b8819e943ddedda3375 Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Thu, 29 Aug 2024 14:41:09 +0800 Subject: hugetlbfs: support tracepoint Add basic tracepoints for {alloc, evict, free}_inode, setattr and fallocate. These can help users to debug hugetlbfs more conveniently. Signed-off-by: Hongbo Li Link: https://lore.kernel.org/r/20240829064110.67884-2-lihongbo22@huawei.com Reviewed-by: Steven Rostedt (Google) Signed-off-by: Christian Brauner --- include/trace/events/hugetlbfs.h | 156 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) create mode 100644 include/trace/events/hugetlbfs.h (limited to 'include/trace') diff --git a/include/trace/events/hugetlbfs.h b/include/trace/events/hugetlbfs.h new file mode 100644 index 000000000000..8331c904a9ba --- /dev/null +++ b/include/trace/events/hugetlbfs.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hugetlbfs + +#if !defined(_TRACE_HUGETLBFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HUGETLBFS_H + +#include + +TRACE_EVENT(hugetlbfs_alloc_inode, + + TP_PROTO(struct inode *inode, struct inode *dir, int mode), + + TP_ARGS(inode, dir, mode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(ino_t, dir) + __field(__u16, mode) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->dir = dir->i_ino; + __entry->mode = mode; + ), + + TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long) __entry->dir, __entry->mode) +); + +DECLARE_EVENT_CLASS(hugetlbfs__inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(__u16, mode) + __field(loff_t, size) + __field(unsigned int, nlink) + __field(unsigned int, seals) + __field(blkcnt_t, blocks) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->mode = inode->i_mode; + __entry->size = inode->i_size; + __entry->nlink = inode->i_nlink; + __entry->seals = HUGETLBFS_I(inode)->seals; + __entry->blocks = inode->i_blocks; + ), + + TP_printk("dev %d,%d ino %lu mode 0%o size %lld nlink %u seals %u blocks %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, + __entry->mode, __entry->size, __entry->nlink, __entry->seals, + (unsigned long long)__entry->blocks) +); + +DEFINE_EVENT(hugetlbfs__inode, hugetlbfs_evict_inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(hugetlbfs__inode, hugetlbfs_free_inode, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +TRACE_EVENT(hugetlbfs_setattr, + + TP_PROTO(struct inode *inode, struct dentry *dentry, + struct iattr *attr), + + TP_ARGS(inode, dentry, attr), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(unsigned int, d_len) + __string(d_name, dentry->d_name.name) + __field(unsigned int, ia_valid) + __field(unsigned int, ia_mode) + __field(loff_t, old_size) + __field(loff_t, ia_size) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->d_len = dentry->d_name.len; + __assign_str(d_name); + __entry->ia_valid = attr->ia_valid; + __entry->ia_mode = attr->ia_mode; + __entry->old_size = inode->i_size; + __entry->ia_size = attr->ia_size; + ), + + TP_printk("dev %d,%d ino %lu name %.*s valid %#x mode 0%o old_size %lld size %lld", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, + __entry->d_len, __get_str(d_name), __entry->ia_valid, __entry->ia_mode, + __entry->old_size, __entry->ia_size) +); + +TRACE_EVENT(hugetlbfs_fallocate, + + TP_PROTO(struct inode *inode, int mode, + loff_t offset, loff_t len, int ret), + + TP_ARGS(inode, mode, offset, len, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, mode) + __field(loff_t, offset) + __field(loff_t, len) + __field(loff_t, size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->mode = mode; + __entry->offset = offset; + __entry->len = len; + __entry->size = inode->i_size; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu mode 0%o offset %lld len %lld size %lld ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long)__entry->ino, __entry->mode, + (unsigned long long)__entry->offset, + (unsigned long long)__entry->len, + (unsigned long long)__entry->size, + __entry->ret) +); + +#endif /* _TRACE_HUGETLBFS_H */ + + /* This part must be outside protection */ +#include -- cgit v1.2.3 From 1afd01db1a76cdd1d96696e3790d66c79621784c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 20 Sep 2024 10:58:00 +0200 Subject: pwm: Add tracing for waveform callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds trace events for the recently introduced waveform callbacks. With the introduction of some helper macros consistency among the different events is ensured. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/1d71879b0de3bf01459c7a9d0f040d43eb5ace56.1726819463.git.u.kleine-koenig@baylibre.com Signed-off-by: Uwe Kleine-König --- include/trace/events/pwm.h | 134 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 126 insertions(+), 8 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/pwm.h b/include/trace/events/pwm.h index 8022701c446d..8ba898fd335c 100644 --- a/include/trace/events/pwm.h +++ b/include/trace/events/pwm.h @@ -8,15 +8,135 @@ #include #include +#define TP_PROTO_pwm(args...) \ + TP_PROTO(struct pwm_device *pwm, args) + +#define TP_ARGS_pwm(args...) \ + TP_ARGS(pwm, args) + +#define TP_STRUCT__entry_pwm(args...) \ + TP_STRUCT__entry( \ + __field(unsigned int, chipid) \ + __field(unsigned int, hwpwm) \ + args) + +#define TP_fast_assign_pwm(args...) \ + TP_fast_assign( \ + __entry->chipid = pwm->chip->id; \ + __entry->hwpwm = pwm->hwpwm; \ + args) + +#define TP_printk_pwm(fmt, args...) \ + TP_printk("pwmchip%u.%u: " fmt, __entry->chipid, __entry->hwpwm, args) + +#define __field_pwmwf(wf) \ + __field(u64, wf ## _period_length_ns) \ + __field(u64, wf ## _duty_length_ns) \ + __field(u64, wf ## _duty_offset_ns) \ + +#define fast_assign_pwmwf(wf) \ + __entry->wf ## _period_length_ns = wf->period_length_ns; \ + __entry->wf ## _duty_length_ns = wf->duty_length_ns; \ + __entry->wf ## _duty_offset_ns = wf->duty_offset_ns + +#define printk_pwmwf_format(wf) \ + "%lld/%lld [+%lld]" + +#define printk_pwmwf_formatargs(wf) \ + __entry->wf ## _duty_length_ns, __entry->wf ## _period_length_ns, __entry->wf ## _duty_offset_ns + +TRACE_EVENT(pwm_round_waveform_tohw, + + TP_PROTO_pwm(const struct pwm_waveform *wf, void *wfhw, int err), + + TP_ARGS_pwm(wf, wfhw, err), + + TP_STRUCT__entry_pwm( + __field_pwmwf(wf) + __field(void *, wfhw) + __field(int, err) + ), + + TP_fast_assign_pwm( + fast_assign_pwmwf(wf); + __entry->wfhw = wfhw; + __entry->err = err; + ), + + TP_printk_pwm(printk_pwmwf_format(wf) " > %p err=%d", + printk_pwmwf_formatargs(wf), __entry->wfhw, __entry->err) +); + +TRACE_EVENT(pwm_round_waveform_fromhw, + + TP_PROTO_pwm(const void *wfhw, struct pwm_waveform *wf, int err), + + TP_ARGS_pwm(wfhw, wf, err), + + TP_STRUCT__entry_pwm( + __field(const void *, wfhw) + __field_pwmwf(wf) + __field(int, err) + ), + + TP_fast_assign_pwm( + __entry->wfhw = wfhw; + fast_assign_pwmwf(wf); + __entry->err = err; + ), + + TP_printk_pwm("%p > " printk_pwmwf_format(wf) " err=%d", + __entry->wfhw, printk_pwmwf_formatargs(wf), __entry->err) +); + +TRACE_EVENT(pwm_read_waveform, + + TP_PROTO_pwm(void *wfhw, int err), + + TP_ARGS_pwm(wfhw, err), + + TP_STRUCT__entry_pwm( + __field(void *, wfhw) + __field(int, err) + ), + + TP_fast_assign_pwm( + __entry->wfhw = wfhw; + __entry->err = err; + ), + + TP_printk_pwm("%p err=%d", + __entry->wfhw, __entry->err) +); + +TRACE_EVENT(pwm_write_waveform, + + TP_PROTO_pwm(const void *wfhw, int err), + + TP_ARGS_pwm(wfhw, err), + + TP_STRUCT__entry_pwm( + __field(const void *, wfhw) + __field(int, err) + ), + + TP_fast_assign_pwm( + __entry->wfhw = wfhw; + __entry->err = err; + ), + + TP_printk_pwm("%p err=%d", + __entry->wfhw, __entry->err) +); + + DECLARE_EVENT_CLASS(pwm, TP_PROTO(struct pwm_device *pwm, const struct pwm_state *state, int err), TP_ARGS(pwm, state, err), - TP_STRUCT__entry( - __field(unsigned int, chipid) - __field(unsigned int, hwpwm) + TP_STRUCT__entry_pwm( __field(u64, period) __field(u64, duty_cycle) __field(enum pwm_polarity, polarity) @@ -24,9 +144,7 @@ DECLARE_EVENT_CLASS(pwm, __field(int, err) ), - TP_fast_assign( - __entry->chipid = pwm->chip->id; - __entry->hwpwm = pwm->hwpwm; + TP_fast_assign_pwm( __entry->period = state->period; __entry->duty_cycle = state->duty_cycle; __entry->polarity = state->polarity; @@ -34,8 +152,8 @@ DECLARE_EVENT_CLASS(pwm, __entry->err = err; ), - TP_printk("pwmchip%u.%u: period=%llu duty_cycle=%llu polarity=%d enabled=%d err=%d", - __entry->chipid, __entry->hwpwm, __entry->period, __entry->duty_cycle, + TP_printk_pwm("period=%llu duty_cycle=%llu polarity=%d enabled=%d err=%d", + __entry->period, __entry->duty_cycle, __entry->polarity, __entry->enabled, __entry->err) ); -- cgit v1.2.3 From fcd4904e2f6908d5c255fa5818bcf8ad32a6f0e8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 5 Oct 2024 19:23:03 +0100 Subject: netfs: Remove call to folio_index() Calling folio_index() is pointless overhead; directly dereferencing folio->index is fine. Signed-off-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20241005182307.3190401-2-willy@infradead.org Signed-off-by: Christian Brauner --- include/trace/events/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 1d7c52821e55..72a208fd4496 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -451,7 +451,7 @@ TRACE_EVENT(netfs_folio, struct address_space *__m = READ_ONCE(folio->mapping); __entry->ino = __m ? __m->host->i_ino : 0; __entry->why = why; - __entry->index = folio_index(folio); + __entry->index = folio->index; __entry->nr = folio_nr_pages(folio); ), -- cgit v1.2.3 From 796a4049640b54cb1daf9e7fe543292c5ca02c74 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 4 Oct 2024 15:33:58 +0100 Subject: netfs: In readahead, put the folio refs as soon extracted netfslib currently defers dropping the ref on the folios it obtains during readahead to after it has started I/O on the basis that we can do it whilst we wait for the I/O to complete, but this runs the risk of the I/O collection racing with this in future. Furthermore, Matthew Wilcox strongly suggests that the refs should be dropped immediately, as readahead_folio() does (netfslib is using __readahead_batch() which doesn't drop the refs). Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Suggested-by: Matthew Wilcox Signed-off-by: David Howells Link: https://lore.kernel.org/r/3771538.1728052438@warthog.procyon.org.uk cc: Jeff Layton cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- include/trace/events/netfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 1d7c52821e55..69975c9c6823 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -172,7 +172,6 @@ EM(netfs_folio_trace_read, "read") \ EM(netfs_folio_trace_read_done, "read-done") \ EM(netfs_folio_trace_read_gaps, "read-gaps") \ - EM(netfs_folio_trace_read_put, "read-put") \ EM(netfs_folio_trace_read_unlock, "read-unlock") \ EM(netfs_folio_trace_redirtied, "redirtied") \ EM(netfs_folio_trace_store, "store") \ -- cgit v1.2.3 From 48bcda6848232667f13b4e97588de488c83c37d4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 3 Oct 2024 18:16:29 -0400 Subject: tracing: Remove definition of trace_*_rcuidle() The trace_*_rcuidle() variant of a tracepoint was to handle places where a tracepoint was located but RCU was not "watching". All those locations have been removed, and RCU should be watching where all tracepoints are located. We can now remove the trace_*_rcuidle() variant. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Cc: Joel Fernandes Link: https://lore.kernel.org/20241003181629.36209057@gandalf.local.home Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (Google) --- include/trace/events/preemptirq.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h index 3f249e150c0c..f99562d2b496 100644 --- a/include/trace/events/preemptirq.h +++ b/include/trace/events/preemptirq.h @@ -43,8 +43,6 @@ DEFINE_EVENT(preemptirq_template, irq_enable, #else #define trace_irq_enable(...) #define trace_irq_disable(...) -#define trace_irq_enable_rcuidle(...) -#define trace_irq_disable_rcuidle(...) #endif #ifdef CONFIG_TRACE_PREEMPT_TOGGLE @@ -58,8 +56,6 @@ DEFINE_EVENT(preemptirq_template, preempt_enable, #else #define trace_preempt_enable(...) #define trace_preempt_disable(...) -#define trace_preempt_enable_rcuidle(...) -#define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ @@ -69,10 +65,6 @@ DEFINE_EVENT(preemptirq_template, preempt_enable, #else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) -#define trace_irq_enable_rcuidle(...) -#define trace_irq_disable_rcuidle(...) #define trace_preempt_enable(...) #define trace_preempt_disable(...) -#define trace_preempt_enable_rcuidle(...) -#define trace_preempt_disable_rcuidle(...) #endif -- cgit v1.2.3 From 0e6caab8db8bc9359d1a8363e1ee9b2205ed704d Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:11 -0400 Subject: tracing: Declare system call tracepoints with TRACE_EVENT_SYSCALL In preparation for allowing system call tracepoints to handle page faults, introduce TRACE_EVENT_SYSCALL to declare the sys_enter/sys_exit tracepoints. Move the common code between __DECLARE_TRACE and __DECLARE_TRACE_SYSCALL into __DECLARE_TRACE_COMMON. This change is not meant to alter the generated code, and only prepares the following modifications. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-2-mathieu.desnoyers@efficios.com Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/bpf_probe.h | 3 +++ include/trace/define_trace.h | 5 +++++ include/trace/events/syscalls.h | 4 ++-- include/trace/perf.h | 3 +++ include/trace/trace_events.h | 28 ++++++++++++++++++++++++++++ 5 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index a2ea11cc912e..c85bbce5aaa5 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -53,6 +53,9 @@ __bpf_trace_##call(void *__data, proto) \ #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + /* * This part is compiled out, it is only here as a build time check * to make sure that if the tracepoint handling changes, the diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index 00723935dcc7..ff5fa17a6259 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -46,6 +46,10 @@ assign, print, reg, unreg) \ DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) +#undef TRACE_EVENT_SYSCALL +#define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, print, reg, unreg) \ + DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) + #undef TRACE_EVENT_NOP #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print) @@ -107,6 +111,7 @@ #undef TRACE_EVENT #undef TRACE_EVENT_FN #undef TRACE_EVENT_FN_COND +#undef TRACE_EVENT_SYSCALL #undef TRACE_EVENT_CONDITION #undef TRACE_EVENT_NOP #undef DEFINE_EVENT_NOP diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index b6e0cbc2c71f..f31ff446b468 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -15,7 +15,7 @@ #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS -TRACE_EVENT_FN(sys_enter, +TRACE_EVENT_SYSCALL(sys_enter, TP_PROTO(struct pt_regs *regs, long id), @@ -41,7 +41,7 @@ TRACE_EVENT_FN(sys_enter, TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY) -TRACE_EVENT_FN(sys_exit, +TRACE_EVENT_SYSCALL(sys_exit, TP_PROTO(struct pt_regs *regs, long ret), diff --git a/include/trace/perf.h b/include/trace/perf.h index 2c11181c82e0..ded997af481e 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -55,6 +55,9 @@ perf_trace_##call(void *__data, proto) \ head, __task); \ } +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + /* * This part is compiled out, it is only here as a build time check * to make sure that if the tracepoint handling changes, the diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index c2f9cabf154d..8bcbb9ee44de 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -45,6 +45,16 @@ PARAMS(print)); \ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); +#undef TRACE_EVENT_SYSCALL +#define TRACE_EVENT_SYSCALL(name, proto, args, tstruct, assign, print, reg, unreg) \ + DECLARE_EVENT_SYSCALL_CLASS(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)); \ + DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); + #include "stages/stage1_struct_define.h" #undef DECLARE_EVENT_CLASS @@ -57,6 +67,9 @@ \ static struct trace_event_class event_class_##name; +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) \ static struct trace_event_call __used \ @@ -117,6 +130,9 @@ tstruct; \ }; +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) @@ -208,6 +224,9 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ .trace = trace_raw_output_##call, \ }; +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ static notrace enum print_line_t \ @@ -265,6 +284,9 @@ static inline notrace int trace_event_get_offsets_##call( \ return __data_size; \ } +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* @@ -409,6 +431,9 @@ trace_event_raw_event_##call(void *__data, proto) \ * fail to compile unless it too is updated. */ +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ static inline void ftrace_test_probe_##call(void) \ @@ -434,6 +459,9 @@ static struct trace_event_class __used __refdata event_class_##call = { \ _TRACE_PERF_INIT(call) \ }; +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ \ -- cgit v1.2.3 From 13d750c2c03e9861e15268574ed2c239cca9c9d5 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:12 -0400 Subject: tracing/ftrace: disable preemption in syscall probe In preparation for allowing system call enter/exit instrumentation to handle page faults, make sure that ftrace can handle this change by explicitly disabling preemption within the ftrace system call tracepoint probes to respect the current expectations within ftrace ring buffer code. This change does not yet allow ftrace to take page faults per se within its probe, but allows its existing probes to adapt to the upcoming change. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-3-mathieu.desnoyers@efficios.com Acked-by: Masami Hiramatsu (Google) Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/trace_events.h | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 8bcbb9ee44de..63071aa5923d 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -263,6 +263,9 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ tstruct \ {} }; +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, name, proto, args, print) @@ -396,11 +399,11 @@ static inline notrace int trace_event_get_offsets_##call( \ #include "stages/stage6_event_callback.h" -#undef DECLARE_EVENT_CLASS -#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ - \ + +#undef __DECLARE_EVENT_CLASS +#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ -trace_event_raw_event_##call(void *__data, proto) \ +do_trace_event_raw_event_##call(void *__data, proto) \ { \ struct trace_event_file *trace_file = __data; \ struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\ @@ -425,15 +428,35 @@ trace_event_raw_event_##call(void *__data, proto) \ \ trace_event_buffer_commit(&fbuffer); \ } + +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +trace_event_raw_event_##call(void *__data, proto) \ +{ \ + do_trace_event_raw_event_##call(__data, args); \ +} + +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +trace_event_raw_event_##call(void *__data, proto) \ +{ \ + preempt_disable_notrace(); \ + do_trace_event_raw_event_##call(__data, args); \ + preempt_enable_notrace(); \ +} + /* * The ftrace_test_probe is compiled out, it is only here as a build time check * to make sure that if the tracepoint handling changes, the ftrace probe will * fail to compile unless it too is updated. */ -#undef DECLARE_EVENT_SYSCALL_CLASS -#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS - #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ static inline void ftrace_test_probe_##call(void) \ @@ -443,6 +466,8 @@ static inline void ftrace_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) +#undef __DECLARE_EVENT_CLASS + #include "stages/stage7_class_define.h" #undef DECLARE_EVENT_CLASS -- cgit v1.2.3 From 65e7462a16cea593025ca3b34c5d74e69b027ee0 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:13 -0400 Subject: tracing/perf: disable preemption in syscall probe In preparation for allowing system call enter/exit instrumentation to handle page faults, make sure that perf can handle this change by explicitly disabling preemption within the perf system call tracepoint probes to respect the current expectations within perf ring buffer code. This change does not yet allow perf to take page faults per se within its probe, but allows its existing probes to adapt to the upcoming change. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-4-mathieu.desnoyers@efficios.com Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/perf.h | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/perf.h b/include/trace/perf.h index ded997af481e..15cde7eac8b4 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -12,10 +12,10 @@ #undef __perf_task #define __perf_task(t) (__task = (t)) -#undef DECLARE_EVENT_CLASS -#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +#undef __DECLARE_EVENT_CLASS +#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ -perf_trace_##call(void *__data, proto) \ +do_perf_trace_##call(void *__data, proto) \ { \ struct trace_event_call *event_call = __data; \ struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\ @@ -55,8 +55,39 @@ perf_trace_##call(void *__data, proto) \ head, __task); \ } +/* + * Define unused __count and __task variables to use @args to pass + * arguments to do_perf_trace_##call. This is needed because the + * macros __perf_count and __perf_task introduce the side-effect to + * store copies into those local variables. + */ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +perf_trace_##call(void *__data, proto) \ +{ \ + u64 __count __attribute__((unused)); \ + struct task_struct *__task __attribute__((unused)); \ + \ + do_perf_trace_##call(__data, args); \ +} + #undef DECLARE_EVENT_SYSCALL_CLASS -#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +perf_trace_##call(void *__data, proto) \ +{ \ + u64 __count __attribute__((unused)); \ + struct task_struct *__task __attribute__((unused)); \ + \ + preempt_disable_notrace(); \ + do_perf_trace_##call(__data, args); \ + preempt_enable_notrace(); \ +} /* * This part is compiled out, it is only here as a build time check @@ -76,4 +107,7 @@ static inline void perf_test_probe_##call(void) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef __DECLARE_EVENT_CLASS + #endif /* CONFIG_PERF_EVENTS */ -- cgit v1.2.3 From 4aadde89d81fbf4cf3105a61dbc48888b819ecfb Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:14 -0400 Subject: tracing/bpf: disable preemption in syscall probe In preparation for allowing system call enter/exit instrumentation to handle page faults, make sure that bpf can handle this change by explicitly disabling preemption within the bpf system call tracepoint probes to respect the current expectations within bpf tracing code. This change does not yet allow bpf to take page faults per se within its probe, but allows its existing probes to adapt to the upcoming change. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-5-mathieu.desnoyers@efficios.com Acked-by: Andrii Nakryiko Tested-by: Andrii Nakryiko # BPF parts Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/bpf_probe.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index c85bbce5aaa5..fec97c93e1c9 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -53,8 +53,18 @@ __bpf_trace_##call(void *__data, proto) \ #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ __BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) +#define __BPF_DECLARE_TRACE_SYSCALL(call, proto, args) \ +static notrace void \ +__bpf_trace_##call(void *__data, proto) \ +{ \ + preempt_disable_notrace(); \ + CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args)); \ + preempt_enable_notrace(); \ +} + #undef DECLARE_EVENT_SYSCALL_CLASS -#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \ + __BPF_DECLARE_TRACE_SYSCALL(call, PARAMS(proto), PARAMS(args)) /* * This part is compiled out, it is only here as a build time check -- cgit v1.2.3 From a3204c740a59bebb3b37a294d83f4e353303a52c Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:16 -0400 Subject: tracing/ftrace: Add might_fault check to syscall probes Add a might_fault() check to validate that the ftrace sys_enter/sys_exit probe callbacks are indeed called from a context where page faults can be handled. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-7-mathieu.desnoyers@efficios.com Acked-by: Masami Hiramatsu (Google) Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 63071aa5923d..4f22136fd465 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -446,6 +446,7 @@ __DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ static notrace void \ trace_event_raw_event_##call(void *__data, proto) \ { \ + might_fault(); \ preempt_disable_notrace(); \ do_trace_event_raw_event_##call(__data, args); \ preempt_enable_notrace(); \ -- cgit v1.2.3 From cdb537ac417938408ee819992f432c410f2d01a2 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:17 -0400 Subject: tracing/perf: Add might_fault check to syscall probes Add a might_fault() check to validate that the perf sys_enter/sys_exit probe callbacks are indeed called from a context where page faults can be handled. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-8-mathieu.desnoyers@efficios.com Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/perf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/perf.h b/include/trace/perf.h index 15cde7eac8b4..a1754b73a8f5 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -84,6 +84,7 @@ perf_trace_##call(void *__data, proto) \ u64 __count __attribute__((unused)); \ struct task_struct *__task __attribute__((unused)); \ \ + might_fault(); \ preempt_disable_notrace(); \ do_perf_trace_##call(__data, args); \ preempt_enable_notrace(); \ -- cgit v1.2.3 From 0850e1bc88b1bdc30f7f0b223a92eb22e5f06be0 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 8 Oct 2024 21:07:18 -0400 Subject: tracing/bpf: Add might_fault check to syscall probes Add a might_fault() check to validate that the bpf sys_enter/sys_exit probe callbacks are indeed called from a context where page faults can be handled. Cc: Michael Jeanson Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Link: https://lore.kernel.org/20241009010718.2050182-9-mathieu.desnoyers@efficios.com Acked-by: Andrii Nakryiko Tested-by: Andrii Nakryiko # BPF parts Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/bpf_probe.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index fec97c93e1c9..183fa2aa2935 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -57,6 +57,7 @@ __bpf_trace_##call(void *__data, proto) \ static notrace void \ __bpf_trace_##call(void *__data, proto) \ { \ + might_fault(); \ preempt_disable_notrace(); \ CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(__data, CAST_TO_U64(args)); \ preempt_enable_notrace(); \ -- cgit v1.2.3 From c86e3c47187ad7fa17f8533a4142453991684b46 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:21 -0400 Subject: fs: tracepoints around multigrain timestamp events Add some tracepoints around various multigrain timestamp events. Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Reviewed-by: Steven Rostedt (Google) Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-6-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- include/trace/events/timestamp.h | 124 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) create mode 100644 include/trace/events/timestamp.h (limited to 'include/trace') diff --git a/include/trace/events/timestamp.h b/include/trace/events/timestamp.h new file mode 100644 index 000000000000..c9e5ec930054 --- /dev/null +++ b/include/trace/events/timestamp.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM timestamp + +#if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TIMESTAMP_H + +#include +#include + +#define CTIME_QUERIED_FLAGS \ + { I_CTIME_QUERIED, "Q" } + +DECLARE_EVENT_CLASS(ctime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + + TP_ARGS(inode, ctime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(u32, ctime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns + ) +); + +DEFINE_EVENT(ctime, inode_set_ctime_to_ts, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +DEFINE_EVENT(ctime, ctime_xchg_skip, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +TRACE_EVENT(ctime_ns_xchg, + TP_PROTO(struct inode *inode, + u32 old, + u32 new, + u32 cur), + + TP_ARGS(inode, old, new, cur), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(u32, gen) + __field(u32, old) + __field(u32, new) + __field(u32, cur) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->old = old; + __entry->new = new; + __entry->cur = cur; + ), + + TP_printk("ino=%d:%d:%ld:%u old=%u:%s new=%u cur=%u:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->old & ~I_CTIME_QUERIED, + __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), + __entry->new, + __entry->cur & ~I_CTIME_QUERIED, + __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) + ) +); + +TRACE_EVENT(fill_mg_cmtime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime, + struct timespec64 *mtime), + + TP_ARGS(inode, ctime, mtime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(time64_t, mtime_s) + __field(u32, ctime_ns) + __field(u32, mtime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->mtime_s = mtime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + __entry->mtime_ns = mtime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u mtime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns, + __entry->mtime_s, __entry->mtime_ns + ) +); +#endif /* _TRACE_TIMESTAMP_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 37f0b47c5143c2957909ced44fc09ffb118c99f7 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 11 Oct 2024 18:17:02 -0700 Subject: mm: khugepaged: fix the arguments order in khugepaged_collapse_file trace point The "addr" and "is_shmem" arguments have different order in TP_PROTO and TP_ARGS. This resulted in the incorrect trace result: text-hugepage-644429 [276] 392092.878683: mm_khugepaged_collapse_file: mm=0xffff20025d52c440, hpage_pfn=0x200678c00, index=512, addr=1, is_shmem=0, filename=text-hugepage, nr=512, result=failed The value of "addr" is wrong because it was treated as bool value, the type of is_shmem. Fix the order in TP_PROTO to keep "addr" is before "is_shmem" since the original patch review suggested this order to achieve best packing. And use "lx" for "addr" instead of "ld" in TP_printk because address is typically shown in hex. After the fix, the trace result looks correct: text-hugepage-7291 [004] 128.627251: mm_khugepaged_collapse_file: mm=0xffff0001328f9500, hpage_pfn=0x20016ea00, index=512, addr=0x400000, is_shmem=0, filename=text-hugepage, nr=512, result=failed Link: https://lkml.kernel.org/r/20241012011702.1084846-1-yang@os.amperecomputing.com Fixes: 4c9473e87e75 ("mm/khugepaged: add tracepoint to collapse_file()") Signed-off-by: Yang Shi Cc: Gautam Menghani Cc: Steven Rostedt (Google) Cc: [6.2+] Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index b5f5369b6300..9d5c00b0285c 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -208,7 +208,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TRACE_EVENT(mm_khugepaged_collapse_file, TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, - bool is_shmem, unsigned long addr, struct file *file, + unsigned long addr, bool is_shmem, struct file *file, int nr, int result), TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( @@ -233,7 +233,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, __entry->result = result; ), - TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s", + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%lx, is_shmem=%d, filename=%s, nr=%d, result=%s", __entry->mm, __entry->hpfn, __entry->index, -- cgit v1.2.3 From 78b2770c935fc1434a95cc17613fe31165b02dfe Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 17 Oct 2024 11:10:55 -0400 Subject: dma-mapping: fix tracing dma_alloc/free with vmalloc'd memory Not all virtual addresses have physical addresses, such as if they were vmalloc'd. Just trace the virtual address instead of trying to trace a physical address. This aligns with the API, and is good enough to associate dma_alloc with dma_free. Fixes: 038eb433dc14 ("dma-mapping: add tracing for dma-mapping API calls") Reported-by: syzbot+b4bfacdec173efaa8567@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/670ebde5.050a0220.d9b66.0154.GAE@google.com/ Signed-off-by: Sean Anderson Signed-off-by: Christoph Hellwig --- include/trace/events/dma.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 569f86a44aaa..b0f41265191c 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -121,7 +121,7 @@ TRACE_EVENT(dma_alloc, TP_STRUCT__entry( __string(device, dev_name(dev)) - __field(u64, phys_addr) + __field(void *, virt_addr) __field(u64, dma_addr) __field(size_t, size) __field(gfp_t, flags) @@ -130,18 +130,18 @@ TRACE_EVENT(dma_alloc, TP_fast_assign( __assign_str(device); - __entry->phys_addr = virt_to_phys(virt_addr); + __entry->virt_addr = virt_addr; __entry->dma_addr = dma_addr; __entry->size = size; __entry->flags = flags; __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu phys_addr=%llx flags=%s attrs=%s", + TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s", __get_str(device), __entry->dma_addr, __entry->size, - __entry->phys_addr, + __entry->virt_addr, show_gfp_flags(__entry->flags), decode_dma_attrs(__entry->attrs)) ); @@ -153,7 +153,7 @@ TRACE_EVENT(dma_free, TP_STRUCT__entry( __string(device, dev_name(dev)) - __field(u64, phys_addr) + __field(void *, virt_addr) __field(u64, dma_addr) __field(size_t, size) __field(unsigned long, attrs) @@ -161,17 +161,17 @@ TRACE_EVENT(dma_free, TP_fast_assign( __assign_str(device); - __entry->phys_addr = virt_to_phys(virt_addr); + __entry->virt_addr = virt_addr; __entry->dma_addr = dma_addr; __entry->size = size; __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu phys_addr=%llx attrs=%s", + TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s", __get_str(device), __entry->dma_addr, __entry->size, - __entry->phys_addr, + __entry->virt_addr, decode_dma_attrs(__entry->attrs)) ); -- cgit v1.2.3 From 247d65fb122ad560be1c8c4d87d7374fb28b0770 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 23 Oct 2024 11:40:10 +0100 Subject: afs: Fix missing subdir edit when renamed between parent dirs When rename moves an AFS subdirectory between parent directories, the subdir also needs a bit of editing: the ".." entry needs updating to point to the new parent (though I don't make use of the info) and the DV needs incrementing by 1 to reflect the change of content. The server also sends a callback break notification on the subdirectory if we have one, but we can take care of recovering the promise next time we access the subdir. This can be triggered by something like: mount -t afs %example.com:xfstest.test20 /xfstest.test/ mkdir /xfstest.test/{aaa,bbb,aaa/ccc} touch /xfstest.test/bbb/ccc/d mv /xfstest.test/{aaa/ccc,bbb/ccc} touch /xfstest.test/bbb/ccc/e When the pathwalk for the second touch hits "ccc", kafs spots that the DV is incorrect and downloads it again (so the fix is not critical). Fix this, if the rename target is a directory and the old and new parents are different, by: (1) Incrementing the DV number of the target locally. (2) Editing the ".." entry in the target to refer to its new parent's vnode ID and uniquifier. Link: https://lore.kernel.org/r/3340431.1729680010@warthog.procyon.org.uk Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") cc: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David Howells Signed-off-by: Christian Brauner --- include/trace/events/afs.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 450c44c83a5d..a0aed1a428a1 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -331,7 +331,11 @@ enum yfs_cm_operation { EM(afs_edit_dir_delete, "delete") \ EM(afs_edit_dir_delete_error, "d_err ") \ EM(afs_edit_dir_delete_inval, "d_invl") \ - E_(afs_edit_dir_delete_noent, "d_nent") + EM(afs_edit_dir_delete_noent, "d_nent") \ + EM(afs_edit_dir_update_dd, "u_ddot") \ + EM(afs_edit_dir_update_error, "u_fail") \ + EM(afs_edit_dir_update_inval, "u_invl") \ + E_(afs_edit_dir_update_nodd, "u_nodd") #define afs_edit_dir_reasons \ EM(afs_edit_dir_for_create, "Create") \ @@ -340,6 +344,7 @@ enum yfs_cm_operation { EM(afs_edit_dir_for_rename_0, "Renam0") \ EM(afs_edit_dir_for_rename_1, "Renam1") \ EM(afs_edit_dir_for_rename_2, "Renam2") \ + EM(afs_edit_dir_for_rename_sub, "RnmSub") \ EM(afs_edit_dir_for_rmdir, "RmDir ") \ EM(afs_edit_dir_for_silly_0, "S_Ren0") \ EM(afs_edit_dir_for_silly_1, "S_Ren1") \ -- cgit v1.2.3 From 5af5fc895fb9deec3d7b225f5bc2bd4949f8bbd5 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 18 Oct 2024 11:00:34 -0400 Subject: dma-mapping: use macros to define events in a class Use a macro to avoid repeating the parameters and arguments for each event in a class. Signed-off-by: Sean Anderson Reviewed-by: Steven Rostedt (Google) Signed-off-by: Christoph Hellwig --- include/trace/events/dma.h | 60 ++++++++++++++++++++++------------------------ 1 file changed, 28 insertions(+), 32 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index b0f41265191c..3d348cea4d7c 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -65,15 +65,14 @@ DECLARE_EVENT_CLASS(dma_map, decode_dma_attrs(__entry->attrs)) ); -DEFINE_EVENT(dma_map, dma_map_page, - TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs)); +#define DEFINE_MAP_EVENT(name) \ +DEFINE_EVENT(dma_map, name, \ + TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr, \ + size_t size, enum dma_data_direction dir, unsigned long attrs), \ + TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs)) -DEFINE_EVENT(dma_map, dma_map_resource, - TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, phys_addr, dma_addr, size, dir, attrs)); +DEFINE_MAP_EVENT(dma_map_page); +DEFINE_MAP_EVENT(dma_map_resource); DECLARE_EVENT_CLASS(dma_unmap, TP_PROTO(struct device *dev, dma_addr_t addr, size_t size, @@ -104,15 +103,14 @@ DECLARE_EVENT_CLASS(dma_unmap, decode_dma_attrs(__entry->attrs)) ); -DEFINE_EVENT(dma_unmap, dma_unmap_page, - TP_PROTO(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, addr, size, dir, attrs)); +#define DEFINE_UNMAP_EVENT(name) \ +DEFINE_EVENT(dma_unmap, name, \ + TP_PROTO(struct device *dev, dma_addr_t addr, size_t size, \ + enum dma_data_direction dir, unsigned long attrs), \ + TP_ARGS(dev, addr, size, dir, attrs)) -DEFINE_EVENT(dma_unmap, dma_unmap_resource, - TP_PROTO(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, addr, size, dir, attrs)); +DEFINE_UNMAP_EVENT(dma_unmap_page); +DEFINE_UNMAP_EVENT(dma_unmap_resource); TRACE_EVENT(dma_alloc, TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, @@ -279,15 +277,14 @@ DECLARE_EVENT_CLASS(dma_sync_single, __entry->size) ); -DEFINE_EVENT(dma_sync_single, dma_sync_single_for_cpu, - TP_PROTO(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir), - TP_ARGS(dev, dma_addr, size, dir)); +#define DEFINE_SYNC_SINGLE_EVENT(name) \ +DEFINE_EVENT(dma_sync_single, name, \ + TP_PROTO(struct device *dev, dma_addr_t dma_addr, size_t size, \ + enum dma_data_direction dir), \ + TP_ARGS(dev, dma_addr, size, dir)) -DEFINE_EVENT(dma_sync_single, dma_sync_single_for_device, - TP_PROTO(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction dir), - TP_ARGS(dev, dma_addr, size, dir)); +DEFINE_SYNC_SINGLE_EVENT(dma_sync_single_for_cpu); +DEFINE_SYNC_SINGLE_EVENT(dma_sync_single_for_device); DECLARE_EVENT_CLASS(dma_sync_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, @@ -326,15 +323,14 @@ DECLARE_EVENT_CLASS(dma_sync_sg, sizeof(unsigned int), sizeof(unsigned int))) ); -DEFINE_EVENT(dma_sync_sg, dma_sync_sg_for_cpu, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir), - TP_ARGS(dev, sg, nents, dir)); +#define DEFINE_SYNC_SG_EVENT(name) \ +DEFINE_EVENT(dma_sync_sg, name, \ + TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, \ + enum dma_data_direction dir), \ + TP_ARGS(dev, sg, nents, dir)) -DEFINE_EVENT(dma_sync_sg, dma_sync_sg_for_device, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir), - TP_ARGS(dev, sg, nents, dir)); +DEFINE_SYNC_SG_EVENT(dma_sync_sg_for_cpu); +DEFINE_SYNC_SG_EVENT(dma_sync_sg_for_device); #endif /* _TRACE_DMA_H */ -- cgit v1.2.3 From 3afff779a725cba914e6caba360b696ae6f90249 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 18 Oct 2024 11:00:35 -0400 Subject: dma-mapping: trace dma_alloc/free direction In preparation for using these tracepoints in a few more places, trace the DMA direction as well. For coherent allocations this is always bidirectional. Signed-off-by: Sean Anderson Reviewed-by: Steven Rostedt (Google) Signed-off-by: Christoph Hellwig --- include/trace/events/dma.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 3d348cea4d7c..267cfa49d9d5 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -114,8 +114,9 @@ DEFINE_UNMAP_EVENT(dma_unmap_resource); TRACE_EVENT(dma_alloc, TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, - size_t size, gfp_t flags, unsigned long attrs), - TP_ARGS(dev, virt_addr, dma_addr, size, flags, attrs), + size_t size, enum dma_data_direction dir, gfp_t flags, + unsigned long attrs), + TP_ARGS(dev, virt_addr, dma_addr, size, dir, flags, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -123,6 +124,7 @@ TRACE_EVENT(dma_alloc, __field(u64, dma_addr) __field(size_t, size) __field(gfp_t, flags) + __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ), @@ -135,8 +137,9 @@ TRACE_EVENT(dma_alloc, __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s", + TP_printk("%s dir=%s dma_addr=%llx size=%zu virt_addr=%p flags=%s attrs=%s", __get_str(device), + decode_dma_data_direction(__entry->dir), __entry->dma_addr, __entry->size, __entry->virt_addr, @@ -146,14 +149,15 @@ TRACE_EVENT(dma_alloc, TRACE_EVENT(dma_free, TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, - size_t size, unsigned long attrs), - TP_ARGS(dev, virt_addr, dma_addr, size, attrs), + size_t size, enum dma_data_direction dir, unsigned long attrs), + TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) __field(void *, virt_addr) __field(u64, dma_addr) __field(size_t, size) + __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ), @@ -162,11 +166,13 @@ TRACE_EVENT(dma_free, __entry->virt_addr = virt_addr; __entry->dma_addr = dma_addr; __entry->size = size; + __entry->dir = dir; __entry->attrs = attrs; ), - TP_printk("%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s", + TP_printk("%s dir=%s dma_addr=%llx size=%zu virt_addr=%p attrs=%s", __get_str(device), + decode_dma_data_direction(__entry->dir), __entry->dma_addr, __entry->size, __entry->virt_addr, -- cgit v1.2.3 From c4484ab86ee00f2d9236e2851621ea02c105f4cc Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 18 Oct 2024 11:00:36 -0400 Subject: dma-mapping: use trace_dma_alloc for dma_alloc* instead of using trace_dma_map In some cases, we use trace_dma_map to trace dma_alloc* functions. This generally follows dma_debug. However, this does not record all of the relevant information for allocations, such as GFP flags. Create new dma_alloc tracepoints for these functions. Note that while dma_alloc_noncontiguous may allocate discontiguous pages (from the CPU's point of view), the device will only see one contiguous mapping. Therefore, we just need to trace dma_addr and size. Signed-off-by: Sean Anderson Reviewed-by: Steven Rostedt (Google) Signed-off-by: Christoph Hellwig --- include/trace/events/dma.h | 99 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 97 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 267cfa49d9d5..7a9606b8934e 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -112,7 +112,7 @@ DEFINE_EVENT(dma_unmap, name, \ DEFINE_UNMAP_EVENT(dma_unmap_page); DEFINE_UNMAP_EVENT(dma_unmap_resource); -TRACE_EVENT(dma_alloc, +DECLARE_EVENT_CLASS(dma_alloc_class, TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, gfp_t flags, unsigned long attrs), @@ -147,7 +147,58 @@ TRACE_EVENT(dma_alloc, decode_dma_attrs(__entry->attrs)) ); -TRACE_EVENT(dma_free, +#define DEFINE_ALLOC_EVENT(name) \ +DEFINE_EVENT(dma_alloc_class, name, \ + TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, \ + size_t size, enum dma_data_direction dir, gfp_t flags, \ + unsigned long attrs), \ + TP_ARGS(dev, virt_addr, dma_addr, size, dir, flags, attrs)) + +DEFINE_ALLOC_EVENT(dma_alloc); +DEFINE_ALLOC_EVENT(dma_alloc_pages); + +TRACE_EVENT(dma_alloc_sgt, + TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size, + enum dma_data_direction dir, gfp_t flags, unsigned long attrs), + TP_ARGS(dev, sgt, size, dir, flags, attrs), + + TP_STRUCT__entry( + __string(device, dev_name(dev)) + __dynamic_array(u64, phys_addrs, sgt->orig_nents) + __field(u64, dma_addr) + __field(size_t, size) + __field(enum dma_data_direction, dir) + __field(gfp_t, flags) + __field(unsigned long, attrs) + ), + + TP_fast_assign( + struct scatterlist *sg; + int i; + + __assign_str(device); + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); + __entry->dma_addr = sg_dma_address(sgt->sgl); + __entry->size = size; + __entry->dir = dir; + __entry->flags = flags; + __entry->attrs = attrs; + ), + + TP_printk("%s dir=%s dma_addr=%llx size=%zu phys_addrs=%s flags=%s attrs=%s", + __get_str(device), + decode_dma_data_direction(__entry->dir), + __entry->dma_addr, + __entry->size, + __print_array(__get_dynamic_array(phys_addrs), + __get_dynamic_array_len(phys_addrs) / + sizeof(u64), sizeof(u64)), + show_gfp_flags(__entry->flags), + decode_dma_attrs(__entry->attrs)) +); + +DECLARE_EVENT_CLASS(dma_free_class, TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, unsigned long attrs), TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs), @@ -179,6 +230,50 @@ TRACE_EVENT(dma_free, decode_dma_attrs(__entry->attrs)) ); +#define DEFINE_FREE_EVENT(name) \ +DEFINE_EVENT(dma_free_class, name, \ + TP_PROTO(struct device *dev, void *virt_addr, dma_addr_t dma_addr, \ + size_t size, enum dma_data_direction dir, unsigned long attrs), \ + TP_ARGS(dev, virt_addr, dma_addr, size, dir, attrs)) + +DEFINE_FREE_EVENT(dma_free); +DEFINE_FREE_EVENT(dma_free_pages); + +TRACE_EVENT(dma_free_sgt, + TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size, + enum dma_data_direction dir), + TP_ARGS(dev, sgt, size, dir), + + TP_STRUCT__entry( + __string(device, dev_name(dev)) + __dynamic_array(u64, phys_addrs, sgt->orig_nents) + __field(u64, dma_addr) + __field(size_t, size) + __field(enum dma_data_direction, dir) + ), + + TP_fast_assign( + struct scatterlist *sg; + int i; + + __assign_str(device); + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); + __entry->dma_addr = sg_dma_address(sgt->sgl); + __entry->size = size; + __entry->dir = dir; + ), + + TP_printk("%s dir=%s dma_addr=%llx size=%zu phys_addrs=%s", + __get_str(device), + decode_dma_data_direction(__entry->dir), + __entry->dma_addr, + __entry->size, + __print_array(__get_dynamic_array(phys_addrs), + __get_dynamic_array_len(phys_addrs) / + sizeof(u64), sizeof(u64))) +); + TRACE_EVENT(dma_map_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs), -- cgit v1.2.3 From 68b6dbf1f441c4eba3b8511728a41cf9b01dca35 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 18 Oct 2024 11:00:37 -0400 Subject: dma-mapping: trace more error paths It can be surprising to the user if DMA functions are only traced on success. On failure, it can be unclear what the source of the problem is. Fix this by tracing all functions even when they fail. Cases where we BUG/WARN are skipped, since those should be sufficiently noisy already. Signed-off-by: Sean Anderson Reviewed-by: Steven Rostedt (Google) Signed-off-by: Christoph Hellwig --- include/trace/events/dma.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index 7a9606b8934e..d8ddc27b6a7c 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -156,6 +156,7 @@ DEFINE_EVENT(dma_alloc_class, name, \ DEFINE_ALLOC_EVENT(dma_alloc); DEFINE_ALLOC_EVENT(dma_alloc_pages); +DEFINE_ALLOC_EVENT(dma_alloc_sgt_err); TRACE_EVENT(dma_alloc_sgt, TP_PROTO(struct device *dev, struct sg_table *sgt, size_t size, @@ -320,6 +321,41 @@ TRACE_EVENT(dma_map_sg, decode_dma_attrs(__entry->attrs)) ); +TRACE_EVENT(dma_map_sg_err, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, + int err, enum dma_data_direction dir, unsigned long attrs), + TP_ARGS(dev, sgl, nents, err, dir, attrs), + + TP_STRUCT__entry( + __string(device, dev_name(dev)) + __dynamic_array(u64, phys_addrs, nents) + __field(int, err) + __field(enum dma_data_direction, dir) + __field(unsigned long, attrs) + ), + + TP_fast_assign( + struct scatterlist *sg; + int i; + + __assign_str(device); + for_each_sg(sgl, sg, nents, i) + ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); + __entry->err = err; + __entry->dir = dir; + __entry->attrs = attrs; + ), + + TP_printk("%s dir=%s dma_addrs=%s err=%d attrs=%s", + __get_str(device), + decode_dma_data_direction(__entry->dir), + __print_array(__get_dynamic_array(phys_addrs), + __get_dynamic_array_len(phys_addrs) / + sizeof(u64), sizeof(u64)), + __entry->err, + decode_dma_attrs(__entry->attrs)) +); + TRACE_EVENT(dma_unmap_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs), -- cgit v1.2.3 From 2946f08ae9ed650b94e0ffebcdfdda8de76bd926 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 18 Oct 2024 17:14:00 +0100 Subject: io_uring: clean up cqe trace points We have too many helpers posting CQEs, instead of tracing completion events before filling in a CQE and thus having to pass all the data, set the CQE first, pass it to the tracing helper and let it extract everything it needs. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/b83c1ca9ee5aed2df0f3bb743bf5ed699cce4c86.1729267437.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 412c9c210a32..fb81c533b310 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -315,20 +315,14 @@ TRACE_EVENT(io_uring_fail_link, * io_uring_complete - called when completing an SQE * * @ctx: pointer to a ring context structure - * @req: pointer to a submitted request - * @user_data: user data associated with the request - * @res: result of the request - * @cflags: completion flags - * @extra1: extra 64-bit data for CQE32 - * @extra2: extra 64-bit data for CQE32 - * + * @req: (optional) pointer to a submitted request + * @cqe: pointer to the filled in CQE being posted */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, - u64 extra1, u64 extra2), +TP_PROTO(struct io_ring_ctx *ctx, void *req, struct io_uring_cqe *cqe), - TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), + TP_ARGS(ctx, req, cqe), TP_STRUCT__entry ( __field( void *, ctx ) @@ -343,11 +337,11 @@ TRACE_EVENT(io_uring_complete, TP_fast_assign( __entry->ctx = ctx; __entry->req = req; - __entry->user_data = user_data; - __entry->res = res; - __entry->cflags = cflags; - __entry->extra1 = extra1; - __entry->extra2 = extra2; + __entry->user_data = cqe->user_data; + __entry->res = cqe->res; + __entry->cflags = cqe->flags; + __entry->extra1 = io_ctx_cqe32(ctx) ? cqe->big_cqe[0] : 0; + __entry->extra2 = io_ctx_cqe32(ctx) ? cqe->big_cqe[1] : 0; ), TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " -- cgit v1.2.3 From 750fd23926f1507cc826b5a4fdd4bfc7283e7723 Mon Sep 17 00:00:00 2001 From: Avadhut Naik Date: Tue, 22 Oct 2024 19:36:27 +0000 Subject: x86/mce: Add wrapper for struct mce to export vendor specific info Currently, exporting new additional machine check error information involves adding new fields for the same at the end of the struct mce. This additional information can then be consumed through mcelog or tracepoint. However, as new MSRs are being added (and will be added in the future) by CPU vendors on their newer CPUs with additional machine check error information to be exported, the size of struct mce will balloon on some CPUs, unnecessarily, since those fields are vendor-specific. Moreover, different CPU vendors may export the additional information in varying sizes. The problem particularly intensifies since struct mce is exposed to userspace as part of UAPI. It's bloating through vendor-specific data should be avoided to limit the information being sent out to userspace. Add a new structure mce_hw_err to wrap the existing struct mce. The same will prevent its ballooning since vendor-specifc data, if any, can now be exported through a union within the wrapper structure and through __dynamic_array in mce_record tracepoint. Furthermore, new internal kernel fields can be added to the wrapper struct without impacting the user space API. [ bp: Restore reverse x-mas tree order of function vars declarations. ] Suggested-by: Borislav Petkov (AMD) Signed-off-by: Avadhut Naik Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Link: https://lore.kernel.org/r/20241022194158.110073-2-avadhut.naik@amd.com --- include/trace/events/mce.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h index f0f7b3cb2041..65aba1afcd07 100644 --- a/include/trace/events/mce.h +++ b/include/trace/events/mce.h @@ -19,9 +19,9 @@ TRACE_EVENT(mce_record, - TP_PROTO(struct mce *m), + TP_PROTO(struct mce_hw_err *err), - TP_ARGS(m), + TP_ARGS(err), TP_STRUCT__entry( __field( u64, mcgcap ) @@ -46,25 +46,25 @@ TRACE_EVENT(mce_record, ), TP_fast_assign( - __entry->mcgcap = m->mcgcap; - __entry->mcgstatus = m->mcgstatus; - __entry->status = m->status; - __entry->addr = m->addr; - __entry->misc = m->misc; - __entry->synd = m->synd; - __entry->ipid = m->ipid; - __entry->ip = m->ip; - __entry->tsc = m->tsc; - __entry->ppin = m->ppin; - __entry->walltime = m->time; - __entry->cpu = m->extcpu; - __entry->cpuid = m->cpuid; - __entry->apicid = m->apicid; - __entry->socketid = m->socketid; - __entry->cs = m->cs; - __entry->bank = m->bank; - __entry->cpuvendor = m->cpuvendor; - __entry->microcode = m->microcode; + __entry->mcgcap = err->m.mcgcap; + __entry->mcgstatus = err->m.mcgstatus; + __entry->status = err->m.status; + __entry->addr = err->m.addr; + __entry->misc = err->m.misc; + __entry->synd = err->m.synd; + __entry->ipid = err->m.ipid; + __entry->ip = err->m.ip; + __entry->tsc = err->m.tsc; + __entry->ppin = err->m.ppin; + __entry->walltime = err->m.time; + __entry->cpu = err->m.extcpu; + __entry->cpuid = err->m.cpuid; + __entry->apicid = err->m.apicid; + __entry->socketid = err->m.socketid; + __entry->cs = err->m.cs; + __entry->bank = err->m.bank; + __entry->cpuvendor = err->m.cpuvendor; + __entry->microcode = err->m.microcode; ), TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR: %016Lx, MISC: %016Lx, SYND: %016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x, microcode: %x", -- cgit v1.2.3 From e52750fb1458ae9ea5860a08ed7a149185bc5b97 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 22 Oct 2024 19:36:28 +0000 Subject: tracing: Add __print_dynamic_array() helper When printing a dynamic array in a trace event, the method is rather ugly. It has the format of: __print_array(__get_dynamic_array(array), __get_dynmaic_array_len(array) / el_size, el_size) Since dynamic arrays are known to the tracing infrastructure, create a helper macro that does the above for you. __print_dynamic_array(array, el_size) Which would expand to the same output. Signed-off-by: Steven Rostedt (Google) Signed-off-by: Avadhut Naik Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Link: https://lore.kernel.org/r/20241022194158.110073-3-avadhut.naik@amd.com --- include/trace/stages/stage3_trace_output.h | 8 ++++++++ include/trace/stages/stage7_class_define.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/trace') diff --git a/include/trace/stages/stage3_trace_output.h b/include/trace/stages/stage3_trace_output.h index c1fb1355d309..1e7b0bef95f5 100644 --- a/include/trace/stages/stage3_trace_output.h +++ b/include/trace/stages/stage3_trace_output.h @@ -119,6 +119,14 @@ trace_print_array_seq(p, array, count, el_size); \ }) +#undef __print_dynamic_array +#define __print_dynamic_array(array, el_size) \ + ({ \ + __print_array(__get_dynamic_array(array), \ + __get_dynamic_array_len(array) / (el_size), \ + (el_size)); \ + }) + #undef __print_hex_dump #define __print_hex_dump(prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) \ diff --git a/include/trace/stages/stage7_class_define.h b/include/trace/stages/stage7_class_define.h index bcb960d16fc0..fcd564a590f4 100644 --- a/include/trace/stages/stage7_class_define.h +++ b/include/trace/stages/stage7_class_define.h @@ -22,6 +22,7 @@ #undef __get_rel_cpumask #undef __get_rel_sockaddr #undef __print_array +#undef __print_dynamic_array #undef __print_hex_dump #undef __get_buf -- cgit v1.2.3 From d4fca1358ea9096f2f6ed942e2cb3a820073dfc1 Mon Sep 17 00:00:00 2001 From: Avadhut Naik Date: Tue, 22 Oct 2024 19:36:29 +0000 Subject: x86/MCE/AMD: Add support for new MCA_SYND{1,2} registers Starting with Zen4, AMD's Scalable MCA systems incorporate two new registers: MCA_SYND1 and MCA_SYND2. These registers will include supplemental error information in addition to the existing MCA_SYND register. The data within these registers is considered valid if MCA_STATUS[SyndV] is set. Userspace error decoding tools like rasdaemon gather related hardware error information through the tracepoints. Therefore, export these two registers through the mce_record tracepoint so that tools like rasdaemon can parse them and output the supplemental error information like FRU text contained in them. [ bp: Massage. ] Signed-off-by: Yazen Ghannam Signed-off-by: Avadhut Naik Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Link: https://lore.kernel.org/r/20241022194158.110073-4-avadhut.naik@amd.com --- include/trace/events/mce.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h index 65aba1afcd07..c1c50df9ecfd 100644 --- a/include/trace/events/mce.h +++ b/include/trace/events/mce.h @@ -43,6 +43,7 @@ TRACE_EVENT(mce_record, __field( u8, bank ) __field( u8, cpuvendor ) __field( u32, microcode ) + __dynamic_array(u8, v_data, sizeof(err->vendor)) ), TP_fast_assign( @@ -65,9 +66,10 @@ TRACE_EVENT(mce_record, __entry->bank = err->m.bank; __entry->cpuvendor = err->m.cpuvendor; __entry->microcode = err->m.microcode; + memcpy(__get_dynamic_array(v_data), &err->vendor, sizeof(err->vendor)); ), - TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, IPID: %016Lx, ADDR: %016Lx, MISC: %016Lx, SYND: %016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x, microcode: %x", + TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016llx, IPID: %016llx, ADDR: %016llx, MISC: %016llx, SYND: %016llx, RIP: %02x:<%016llx>, TSC: %llx, PPIN: %llx, vendor: %u, CPUID: %x, time: %llu, socket: %u, APIC: %x, microcode: %x, vendor data: %s", __entry->cpu, __entry->mcgcap, __entry->mcgstatus, __entry->bank, __entry->status, @@ -83,7 +85,8 @@ TRACE_EVENT(mce_record, __entry->walltime, __entry->socketid, __entry->apicid, - __entry->microcode) + __entry->microcode, + __print_dynamic_array(v_data, sizeof(u8))) ); #endif /* _TRACE_MCE_H */ -- cgit v1.2.3 From 654ced4a13774e5aec4d9466c97d22df7cb1e60b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 31 Oct 2024 11:20:54 -0400 Subject: tracing: Introduce tracepoint_is_faultable() Introduce a "faultable" flag within the extended structure to know whether a tracepoint needs rcu tasks trace grace period before reclaim. This can be queried using tracepoint_is_faultable(). Acked-by: Andrii Nakryiko Tested-by: Jordan Rife Cc: Michael Jeanson Cc: Thomas Gleixner Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes Cc: Jordan Rife Cc: linux-trace-kernel@vger.kernel.org Link: https://lore.kernel.org/20241031152056.744137-3-mathieu.desnoyers@efficios.com Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/trace/define_trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index ff5fa17a6259..63fea2218afa 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -48,7 +48,7 @@ #undef TRACE_EVENT_SYSCALL #define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, print, reg, unreg) \ - DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args)) + DEFINE_TRACE_SYSCALL(name, reg, unreg, PARAMS(proto), PARAMS(args)) #undef TRACE_EVENT_NOP #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print) -- cgit v1.2.3 From ad37bcd965fda43f34cf5cc051f5d310880bd1e7 Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Wed, 30 Oct 2024 16:04:25 +0000 Subject: rust: add tracepoint support Make it possible to have Rust code call into tracepoints defined by C code. It is still required that the tracepoint is declared in a C header, and that this header is included in the input to bindgen. Instead of calling __DO_TRACE directly, the exported rust_do_trace_ function calls an inline helper function. This is because the `cond` argument does not exist at the callsite of DEFINE_RUST_DO_TRACE. __DECLARE_TRACE always emits an inline static and an extern declaration that is only used when CREATE_RUST_TRACE_POINTS is set. These should not end up in the final binary so it is not a problem that they sometimes are emitted without a user. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Jason Baron Cc: Ard Biesheuvel Cc: Miguel Ojeda Cc: Alex Gaynor Cc: Wedson Almeida Filho Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " Cc: Benno Lossin Cc: Andreas Hindborg Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Sean Christopherson Cc: Uros Bizjak Cc: Catalin Marinas Cc: Will Deacon Cc: Marc Zyngier Cc: Oliver Upton Cc: Mark Rutland Cc: Ryan Roberts Cc: Fuad Tabba Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Anup Patel Cc: Andrew Jones Cc: Alexandre Ghiti Cc: Conor Dooley Cc: Samuel Holland Cc: Huacai Chen Cc: WANG Xuerui Cc: Bibo Mao Cc: Tiezhu Yang Cc: Andrew Morton Cc: Tianrui Zhao Link: https://lore.kernel.org/20241030-tracepoint-v12-2-eec7f0f8ad22@google.com Reviewed-by: Carlos Llamas Reviewed-by: Gary Guo Reviewed-by: Boqun Feng Signed-off-by: Alice Ryhl Signed-off-by: Steven Rostedt (Google) --- include/trace/define_trace.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/trace') diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index ff5fa17a6259..0557626b6f6a 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -76,6 +76,13 @@ #define DECLARE_TRACE(name, proto, args) \ DEFINE_TRACE(name, PARAMS(proto), PARAMS(args)) +/* If requested, create helpers for calling these tracepoints from Rust. */ +#ifdef CREATE_RUST_TRACE_POINTS +#undef DEFINE_RUST_DO_TRACE +#define DEFINE_RUST_DO_TRACE(name, proto, args) \ + __DEFINE_RUST_DO_TRACE(name, PARAMS(proto), PARAMS(args)) +#endif + #undef TRACE_INCLUDE #undef __TRACE_INCLUDE @@ -134,6 +141,11 @@ # undef UNDEF_TRACE_INCLUDE_PATH #endif +#ifdef CREATE_RUST_TRACE_POINTS +# undef DEFINE_RUST_DO_TRACE +# define DEFINE_RUST_DO_TRACE(name, proto, args) +#endif + /* We may be processing more files */ #define CREATE_TRACE_POINTS -- cgit v1.2.3 From 91d39024e1b02914cc5e2dbc137908e29b269ce4 Mon Sep 17 00:00:00 2001 From: Alice Ryhl Date: Wed, 30 Oct 2024 16:04:26 +0000 Subject: rust: samples: add tracepoint to Rust sample This updates the Rust printing sample to invoke a tracepoint. This ensures that we have a user in-tree from the get-go even though the patch is being merged before its real user. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Jason Baron Cc: Ard Biesheuvel Cc: Miguel Ojeda Cc: Alex Gaynor Cc: Wedson Almeida Filho Cc: Gary Guo Cc: " =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= " Cc: Benno Lossin Cc: Andreas Hindborg Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Sean Christopherson Cc: Uros Bizjak Cc: Catalin Marinas Cc: Will Deacon Cc: Marc Zyngier Cc: Oliver Upton Cc: Mark Rutland Cc: Ryan Roberts Cc: Fuad Tabba Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Anup Patel Cc: Andrew Jones Cc: Alexandre Ghiti Cc: Conor Dooley Cc: Samuel Holland Cc: Huacai Chen Cc: WANG Xuerui Cc: Bibo Mao Cc: Tiezhu Yang Cc: Andrew Morton Cc: Tianrui Zhao Link: https://lore.kernel.org/20241030-tracepoint-v12-3-eec7f0f8ad22@google.com Reviewed-by: Boqun Feng Signed-off-by: Alice Ryhl Signed-off-by: Steven Rostedt (Google) --- include/trace/events/rust_sample.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/trace/events/rust_sample.h (limited to 'include/trace') diff --git a/include/trace/events/rust_sample.h b/include/trace/events/rust_sample.h new file mode 100644 index 000000000000..dbc80ca2e465 --- /dev/null +++ b/include/trace/events/rust_sample.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Tracepoints for `samples/rust/rust_print.rs`. + * + * Copyright (C) 2024 Google, Inc. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rust_sample + +#if !defined(_RUST_SAMPLE_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _RUST_SAMPLE_TRACE_H + +#include + +TRACE_EVENT(rust_sample_loaded, + TP_PROTO(int magic_number), + TP_ARGS(magic_number), + TP_STRUCT__entry( + __field(int, magic_number) + ), + TP_fast_assign( + __entry->magic_number = magic_number; + ), + TP_printk("magic=%d", __entry->magic_number) +); + +#endif /* _RUST_SAMPLE_TRACE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 0aa3ef3637920799f1b2f67dfff0d698127444ac Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 9 Oct 2024 17:35:50 -0700 Subject: memcg: add tracing for memcg stat updates The memcg stats are maintained in rstat infrastructure which provides very fast updates side and reasonable read side. However memcg added plethora of stats and made the read side, which is cgroup rstat flush, very slow. To solve that, threshold was added in the memcg stats read side i.e. no need to flush the stats if updates are within the threshold. This threshold based improvement worked for sometime but more stats were added to memcg and also the read codepath was getting triggered in the performance sensitive paths which made threshold based ratelimiting ineffective. We need more visibility into the hot and cold stats i.e. stats with a lot of updates. Let's add trace to get that visibility. [shakeel.butt@linux.dev: use unsigned long type for memcg_rstat_events, per Yosry] Link: https://lkml.kernel.org/r/20241015213721.3804209-1-shakeel.butt@linux.dev Link: https://lkml.kernel.org/r/20241010003550.3695245-1-shakeel.butt@linux.dev Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: Yosry Ahmed Acked-by: Johannes Weiner Reviewed-by: T.J. Mercier Cc: Michal Hocko Cc: Muchun Song Cc: JP Kobryn Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/trace/events/memcg.h | 81 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) create mode 100644 include/trace/events/memcg.h (limited to 'include/trace') diff --git a/include/trace/events/memcg.h b/include/trace/events/memcg.h new file mode 100644 index 000000000000..8667e57816d2 --- /dev/null +++ b/include/trace/events/memcg.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM memcg + +#if !defined(_TRACE_MEMCG_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MEMCG_H + +#include +#include + + +DECLARE_EVENT_CLASS(memcg_rstat_stats, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val), + + TP_STRUCT__entry( + __field(u64, id) + __field(int, item) + __field(int, val) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->item = item; + __entry->val = val; + ), + + TP_printk("memcg_id=%llu item=%d val=%d", + __entry->id, __entry->item, __entry->val) +); + +DEFINE_EVENT(memcg_rstat_stats, mod_memcg_state, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val) +); + +DEFINE_EVENT(memcg_rstat_stats, mod_memcg_lruvec_state, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val) +); + +DECLARE_EVENT_CLASS(memcg_rstat_events, + + TP_PROTO(struct mem_cgroup *memcg, int item, unsigned long val), + + TP_ARGS(memcg, item, val), + + TP_STRUCT__entry( + __field(u64, id) + __field(int, item) + __field(unsigned long, val) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->item = item; + __entry->val = val; + ), + + TP_printk("memcg_id=%llu item=%d val=%lu", + __entry->id, __entry->item, __entry->val) +); + +DEFINE_EVENT(memcg_rstat_events, count_memcg_events, + + TP_PROTO(struct mem_cgroup *memcg, int item, unsigned long val), + + TP_ARGS(memcg, item, val) +); + + +#endif /* _TRACE_MEMCG_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 1f2d03cc535138b7cdbed0122cdc0f9e9626c6bf Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Fri, 11 Oct 2024 21:49:28 +0900 Subject: vmscan: add a vmscan event for reclaim_pages reclaim_folio_list uses a dummy reclaim_stat and is not being used. To know the memory stat, add a new trace event. This is useful how how many pages are not reclaimed or why. This is an example: mm_vmscan_reclaim_pages: nid=0 nr_scanned=112 nr_reclaimed=112 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=0 nr_unmap_fail=0 Currently reclaim_folio_list is only called by reclaim_pages, and reclaim_pages is used by damon and madvise. In the latest Android, reclaim_pages is also used by shmem to reclaim all pages in a address_space. [jaewon31.kim@samsung.com: use sc.nr_scanned rather than new counting] Link: https://lkml.kernel.org/r/20241016143227.961162-1-jaewon31.kim@samsung.com Link: https://lkml.kernel.org/r/20241011124928.1224813-1-jaewon31.kim@samsung.com Signed-off-by: Jaewon Kim Acked-by: Vlastimil Babka Cc: Jaewon Kim Cc: Kalesh Singh Cc: Minchan Kim Cc: SeongJae Park Signed-off-by: Andrew Morton --- include/trace/events/vmscan.h | 45 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 1a488c30afa5..490958fa10de 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -346,6 +346,51 @@ TRACE_EVENT(mm_vmscan_write_folio, show_reclaim_flags(__entry->reclaim_flags)) ); +TRACE_EVENT(mm_vmscan_reclaim_pages, + + TP_PROTO(int nid, + unsigned long nr_scanned, unsigned long nr_reclaimed, + struct reclaim_stat *stat), + + TP_ARGS(nid, nr_scanned, nr_reclaimed, stat), + + TP_STRUCT__entry( + __field(int, nid) + __field(unsigned long, nr_scanned) + __field(unsigned long, nr_reclaimed) + __field(unsigned long, nr_dirty) + __field(unsigned long, nr_writeback) + __field(unsigned long, nr_congested) + __field(unsigned long, nr_immediate) + __field(unsigned int, nr_activate0) + __field(unsigned int, nr_activate1) + __field(unsigned long, nr_ref_keep) + __field(unsigned long, nr_unmap_fail) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->nr_scanned = nr_scanned; + __entry->nr_reclaimed = nr_reclaimed; + __entry->nr_dirty = stat->nr_dirty; + __entry->nr_writeback = stat->nr_writeback; + __entry->nr_congested = stat->nr_congested; + __entry->nr_immediate = stat->nr_immediate; + __entry->nr_activate0 = stat->nr_activate[0]; + __entry->nr_activate1 = stat->nr_activate[1]; + __entry->nr_ref_keep = stat->nr_ref_keep; + __entry->nr_unmap_fail = stat->nr_unmap_fail; + ), + + TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld", + __entry->nid, + __entry->nr_scanned, __entry->nr_reclaimed, + __entry->nr_dirty, __entry->nr_writeback, + __entry->nr_congested, __entry->nr_immediate, + __entry->nr_activate0, __entry->nr_activate1, + __entry->nr_ref_keep, __entry->nr_unmap_fail) +); + TRACE_EVENT(mm_vmscan_lru_shrink_inactive, TP_PROTO(int nid, -- cgit v1.2.3 From fc9de52de38f656399d2ce40f7349a6b5f86e787 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 6 Nov 2024 13:03:22 +0000 Subject: rxrpc: Fix missing locking causing hanging calls If a call gets aborted (e.g. because kafs saw a signal) between it being queued for connection and the I/O thread picking up the call, the abort will be prioritised over the connection and it will be removed from local->new_client_calls by rxrpc_disconnect_client_call() without a lock being held. This may cause other calls on the list to disappear if a race occurs. Fix this by taking the client_call_lock when removing a call from whatever list its ->wait_link happens to be on. Signed-off-by: David Howells cc: linux-afs@lists.infradead.org Reported-by: Marc Dionne Fixes: 9d35d880e0e4 ("rxrpc: Move client call connection to the I/O thread") Link: https://patch.msgid.link/726660.1730898202@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- include/trace/events/rxrpc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a1b126a6b0d7..cc22596c7250 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -287,6 +287,7 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ + EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ E_(rxrpc_call_see_zap, "SEE zap ") #define rxrpc_txqueue_traces \ -- cgit v1.2.3 From 93970b6a143bd9f184ebab37c5862a204fb5690e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 29 Oct 2024 15:21:43 -0400 Subject: sunrpc: remove newlines from tracepoints Tracepoint strings don't require newlines (and in fact, they are undesirable). Signed-off-by: Jeff Layton Acked-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 5e8495216689..b13dc275ef4a 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -719,7 +719,7 @@ TRACE_EVENT(rpc_xdr_overflow, ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER - " %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + " %sv%d %s requested=%zu p=%p end=%p xdr=[%p,%zu]/%u/[%p,%zu]/%u", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->requested, __entry->p, __entry->end, @@ -777,7 +777,7 @@ TRACE_EVENT(rpc_xdr_alignment, ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER - " %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u\n", + " %sv%d %s offset=%zu copied=%u xdr=[%p,%zu]/%u/[%p,%zu]/%u", __entry->task_id, __entry->client_id, __get_str(progname), __entry->version, __get_str(procedure), __entry->offset, __entry->copied, -- cgit v1.2.3 From f914ac96ee8828368f5a24553e75216d76da0b42 Mon Sep 17 00:00:00 2001 From: JP Kobryn Date: Mon, 28 Oct 2024 19:11:06 -0700 Subject: memcg: add flush tracepoint This tracepoint gives visibility on how often the flushing of memcg stats occurs and contains info on whether it was forced, skipped, and the value of stats updated. It can help with understanding how readers are affected by having to perform the flush, and the effectiveness of the flush by inspecting the number of stats updated. Paired with the recently added tracepoints for tracing rstat updates, it can also help show correlation where stats exceed thresholds frequently. Link: https://lkml.kernel.org/r/20241029021106.25587-3-inwardvessel@gmail.com Signed-off-by: JP Kobryn Reviewed-by: Yosry Ahmed Acked-by: Shakeel Butt Cc: Johannes Weiner Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/trace/events/memcg.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/memcg.h b/include/trace/events/memcg.h index 8667e57816d2..dfe2f51019b4 100644 --- a/include/trace/events/memcg.h +++ b/include/trace/events/memcg.h @@ -74,6 +74,31 @@ DEFINE_EVENT(memcg_rstat_events, count_memcg_events, TP_ARGS(memcg, item, val) ); +TRACE_EVENT(memcg_flush_stats, + + TP_PROTO(struct mem_cgroup *memcg, s64 stats_updates, + bool force, bool needs_flush), + + TP_ARGS(memcg, stats_updates, force, needs_flush), + + TP_STRUCT__entry( + __field(u64, id) + __field(s64, stats_updates) + __field(bool, force) + __field(bool, needs_flush) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->stats_updates = stats_updates; + __entry->force = force; + __entry->needs_flush = needs_flush; + ), + + TP_printk("memcg_id=%llu stats_updates=%lld force=%d needs_flush=%d", + __entry->id, __entry->stats_updates, + __entry->force, __entry->needs_flush) +); #endif /* _TRACE_MEMCG_H */ -- cgit v1.2.3 From c28b97f53be7b598ae5fb47cc9dc80912019d7a8 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 24 Sep 2024 17:12:32 +0100 Subject: btrfs: qgroups: remove bytenr field from struct btrfs_qgroup_extent_record Now that we track qgroup extent records in a xarray we don't need to have a "bytenr" field in struct btrfs_qgroup_extent_record, since we can get it from the index of the record in the xarray. So remove the field and grab the bytenr from either the index key or any other place where it's available (delayed refs). This reduces the size of struct btrfs_qgroup_extent_record from 40 bytes down to 32 bytes, meaning that we now can store 128 instances of this structure instead of 102 per 4K page. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index af6b3827fb1d..8d2ff32fb3b0 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1706,9 +1706,10 @@ DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data, DECLARE_EVENT_CLASS(btrfs_qgroup_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, - const struct btrfs_qgroup_extent_record *rec), + const struct btrfs_qgroup_extent_record *rec, + u64 bytenr), - TP_ARGS(fs_info, rec), + TP_ARGS(fs_info, rec, bytenr), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) @@ -1716,7 +1717,7 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent, ), TP_fast_assign_btrfs(fs_info, - __entry->bytenr = rec->bytenr; + __entry->bytenr = bytenr; __entry->num_bytes = rec->num_bytes; ), @@ -1727,17 +1728,19 @@ DECLARE_EVENT_CLASS(btrfs_qgroup_extent, DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents, TP_PROTO(const struct btrfs_fs_info *fs_info, - const struct btrfs_qgroup_extent_record *rec), + const struct btrfs_qgroup_extent_record *rec, + u64 bytenr), - TP_ARGS(fs_info, rec) + TP_ARGS(fs_info, rec, bytenr) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, - const struct btrfs_qgroup_extent_record *rec), + const struct btrfs_qgroup_extent_record *rec, + u64 bytenr), - TP_ARGS(fs_info, rec) + TP_ARGS(fs_info, rec, bytenr) ); TRACE_EVENT(qgroup_num_dirty_extents, -- cgit v1.2.3 From b628c139519ae0e5453e5327161a41bae966201d Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Thu, 3 Oct 2024 15:27:27 +0100 Subject: btrfs: remove unused btrfs_try_tree_write_lock() btrfs_try_tree_write_lock() has been unused since commit 50b21d7a066f ("btrfs: submit a writeback bio per extent_buffer"). Remove it as we don't need it anymore. Reviewed-by: Christoph Hellwig Reviewed-by: Qu Wenruo Signed-off-by: Dr. David Alan Gilbert Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 8d2ff32fb3b0..bd515415ea8b 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2344,7 +2344,6 @@ DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_unlock_blocking); DEFINE_BTRFS_LOCK_EVENT(btrfs_set_lock_blocking_read); DEFINE_BTRFS_LOCK_EVENT(btrfs_set_lock_blocking_write); DEFINE_BTRFS_LOCK_EVENT(btrfs_try_tree_read_lock); -DEFINE_BTRFS_LOCK_EVENT(btrfs_try_tree_write_lock); DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_lock_atomic); DECLARE_EVENT_CLASS(btrfs__space_info_update, -- cgit v1.2.3 From 70a5f9e266cf1f544f33ce56f1eee634d79f3030 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 4 Sep 2024 17:03:43 +0100 Subject: btrfs: simplify tracking progress for the extent map shrinker Now that the extent map shrinker can only be run by a single task (as a work queue item) there is no need to keep the progress of the shrinker protected by a spinlock and passing the progress to trace events as parameters. So remove the lock and simplify the arguments for the trace events. Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index bd515415ea8b..879016b4e391 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2555,10 +2555,9 @@ TRACE_EVENT(btrfs_extent_map_shrinker_count, TRACE_EVENT(btrfs_extent_map_shrinker_scan_enter, - TP_PROTO(const struct btrfs_fs_info *fs_info, long nr_to_scan, long nr, - u64 last_root_id, u64 last_ino), + TP_PROTO(const struct btrfs_fs_info *fs_info, long nr), - TP_ARGS(fs_info, nr_to_scan, nr, last_root_id, last_ino), + TP_ARGS(fs_info, nr), TP_STRUCT__entry_btrfs( __field( long, nr_to_scan ) @@ -2568,10 +2567,11 @@ TRACE_EVENT(btrfs_extent_map_shrinker_scan_enter, ), TP_fast_assign_btrfs(fs_info, - __entry->nr_to_scan = nr_to_scan; + __entry->nr_to_scan = \ + atomic64_read(&fs_info->extent_map_shrinker_nr_to_scan); __entry->nr = nr; - __entry->last_root_id = last_root_id; - __entry->last_ino = last_ino; + __entry->last_root_id = fs_info->extent_map_shrinker_last_root; + __entry->last_ino = fs_info->extent_map_shrinker_last_ino; ), TP_printk_btrfs("nr_to_scan=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", @@ -2581,10 +2581,9 @@ TRACE_EVENT(btrfs_extent_map_shrinker_scan_enter, TRACE_EVENT(btrfs_extent_map_shrinker_scan_exit, - TP_PROTO(const struct btrfs_fs_info *fs_info, long nr_dropped, long nr, - u64 last_root_id, u64 last_ino), + TP_PROTO(const struct btrfs_fs_info *fs_info, long nr_dropped, long nr), - TP_ARGS(fs_info, nr_dropped, nr, last_root_id, last_ino), + TP_ARGS(fs_info, nr_dropped, nr), TP_STRUCT__entry_btrfs( __field( long, nr_dropped ) @@ -2596,8 +2595,8 @@ TRACE_EVENT(btrfs_extent_map_shrinker_scan_exit, TP_fast_assign_btrfs(fs_info, __entry->nr_dropped = nr_dropped; __entry->nr = nr; - __entry->last_root_id = last_root_id; - __entry->last_ino = last_ino; + __entry->last_root_id = fs_info->extent_map_shrinker_last_root; + __entry->last_ino = fs_info->extent_map_shrinker_last_ino; ), TP_printk_btrfs("nr_dropped=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", -- cgit v1.2.3 From e7fa845010f12bb98251a2bf9dcf39fd601f9424 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 5 Sep 2024 11:31:49 +0100 Subject: btrfs: rename extent map shrinker members from struct btrfs_fs_info The names for the members of struct btrfs_fs_info related to the extent map shrinker are a bit too long, so rename them to be shorter by replacing the "extent_map_" prefix with the "em_" prefix. Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 879016b4e391..4df93ca9b7a8 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2568,10 +2568,10 @@ TRACE_EVENT(btrfs_extent_map_shrinker_scan_enter, TP_fast_assign_btrfs(fs_info, __entry->nr_to_scan = \ - atomic64_read(&fs_info->extent_map_shrinker_nr_to_scan); + atomic64_read(&fs_info->em_shrinker_nr_to_scan); __entry->nr = nr; - __entry->last_root_id = fs_info->extent_map_shrinker_last_root; - __entry->last_ino = fs_info->extent_map_shrinker_last_ino; + __entry->last_root_id = fs_info->em_shrinker_last_root; + __entry->last_ino = fs_info->em_shrinker_last_ino; ), TP_printk_btrfs("nr_to_scan=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", @@ -2595,8 +2595,8 @@ TRACE_EVENT(btrfs_extent_map_shrinker_scan_exit, TP_fast_assign_btrfs(fs_info, __entry->nr_dropped = nr_dropped; __entry->nr = nr; - __entry->last_root_id = fs_info->extent_map_shrinker_last_root; - __entry->last_ino = fs_info->extent_map_shrinker_last_ino; + __entry->last_root_id = fs_info->em_shrinker_last_root; + __entry->last_ino = fs_info->em_shrinker_last_ino; ), TP_printk_btrfs("nr_dropped=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", -- cgit v1.2.3 From 8b9a7bd4d6c83300e50bb1d7071c6032a07e2fed Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 6 Nov 2024 13:00:45 +0000 Subject: rxrpc: Add a tracepoint for aborts being proposed Add a tracepoint to rxrpc to trace the proposal of an abort. The abort is performed asynchronously by the I/O thread. Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/726356.1730898045@warthog.procyon.org.uk Signed-off-by: Jakub Kicinski --- include/trace/events/rxrpc.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index cc22596c7250..d03e0bd8c028 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -773,6 +773,31 @@ TRACE_EVENT(rxrpc_rx_done, TP_printk("r=%d a=%d", __entry->result, __entry->abort_code) ); +TRACE_EVENT(rxrpc_abort_call, + TP_PROTO(const struct rxrpc_call *call, int abort_code), + + TP_ARGS(call, abort_code), + + TP_STRUCT__entry( + __field(unsigned int, call_nr) + __field(enum rxrpc_abort_reason, why) + __field(int, abort_code) + __field(int, error) + ), + + TP_fast_assign( + __entry->call_nr = call->debug_id; + __entry->why = call->send_abort_why; + __entry->abort_code = abort_code; + __entry->error = call->send_abort_err; + ), + + TP_printk("c=%08x a=%d e=%d %s", + __entry->call_nr, + __entry->abort_code, __entry->error, + __print_symbolic(__entry->why, rxrpc_abort_reasons)) + ); + TRACE_EVENT(rxrpc_abort, TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why, u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error), -- cgit v1.2.3 From 9b5c87d47949292ff21ee2fadd1e83820662a430 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 5 Nov 2024 12:34:57 +0100 Subject: mm: mmap_lock: check trace_mmap_lock_$type_enabled() instead of regcount Since 7d6be67cfdd4 ("mm: mmap_lock: replace get_memcg_path_buf() with on-stack buffer") we use trace_mmap_lock_reg()/unreg() only to maintain an atomic reg_refcount which is checked to avoid performing get_mm_memcg_path() in case none of the tracepoints using it is enabled. This can be achieved directly by putting all the work needed for the tracepoint behind the trace_mmap_lock_##type##_enabled(), as suggested by Documentation/trace/tracepoints.rst and with the following advantages: - uses the tracepoint's static key instead of evaluating a branch - the check tracepoint specific, not shared by all of them - we can get rid of trace_mmap_lock_reg()/unreg() completely Thus use the trace_..._enabled() check and remove unnecessary code. Link: https://lkml.kernel.org/r/20241105113456.95066-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Axel Rasmussen Cc: Tetsuo Handa Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Signed-off-by: Andrew Morton --- include/trace/events/mmap_lock.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h index f2827f98a44f..bc2e3ad787b3 100644 --- a/include/trace/events/mmap_lock.h +++ b/include/trace/events/mmap_lock.h @@ -10,9 +10,6 @@ struct mm_struct; -extern int trace_mmap_lock_reg(void); -extern void trace_mmap_lock_unreg(void); - DECLARE_EVENT_CLASS(mmap_lock, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), @@ -40,16 +37,15 @@ DECLARE_EVENT_CLASS(mmap_lock, ); #define DEFINE_MMAP_LOCK_EVENT(name) \ - DEFINE_EVENT_FN(mmap_lock, name, \ + DEFINE_EVENT(mmap_lock, name, \ TP_PROTO(struct mm_struct *mm, const char *memcg_path, \ bool write), \ - TP_ARGS(mm, memcg_path, write), \ - trace_mmap_lock_reg, trace_mmap_lock_unreg) + TP_ARGS(mm, memcg_path, write)) DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking); DEFINE_MMAP_LOCK_EVENT(mmap_lock_released); -TRACE_EVENT_FN(mmap_lock_acquire_returned, +TRACE_EVENT(mmap_lock_acquire_returned, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, bool success), @@ -76,9 +72,7 @@ TRACE_EVENT_FN(mmap_lock_acquire_returned, __get_str(memcg_path), __entry->write ? "true" : "false", __entry->success ? "true" : "false" - ), - - trace_mmap_lock_reg, trace_mmap_lock_unreg + ) ); #endif /* _TRACE_MMAP_LOCK_H */ -- cgit v1.2.3 From 6975c1a486a40446b5bc77a89d9c520f8296fd08 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2024 18:00:39 +0100 Subject: block: remove the ioprio field from struct request The request ioprio is only initialized from the first attached bio, so requests without a bio already never set it. Directly use the bio field instead. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20241112170050.1612998-3-hch@lst.de Signed-off-by: Jens Axboe --- include/trace/events/block.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 1527d5d45e01..bd0ea07338eb 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -99,7 +99,7 @@ TRACE_EVENT(block_rq_requeue, __entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); - __entry->ioprio = rq->ioprio; + __entry->ioprio = req_get_ioprio(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; @@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(block_rq_completion, __entry->sector = blk_rq_pos(rq); __entry->nr_sector = nr_bytes >> 9; __entry->error = blk_status_to_errno(error); - __entry->ioprio = rq->ioprio; + __entry->ioprio = req_get_ioprio(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; @@ -209,7 +209,7 @@ DECLARE_EVENT_CLASS(block_rq, __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); __entry->bytes = blk_rq_bytes(rq); - __entry->ioprio = rq->ioprio; + __entry->ioprio = req_get_ioprio(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags); __get_str(cmd)[0] = '\0'; -- cgit v1.2.3 From 948ccbd95016f50ce01df5eef9440eede3b8c713 Mon Sep 17 00:00:00 2001 From: Xianglai Li Date: Wed, 13 Nov 2024 16:18:26 +0800 Subject: LoongArch: KVM: Add iocsr and mmio bus simulation in kernel Add iocsr and mmio memory read and write simulation to the kernel. When the VM accesses the device address space through iocsr instructions or mmio, it does not need to return to the qemu user mode but can directly completes the access in the kernel mode. Signed-off-by: Tianrui Zhao Signed-off-by: Xianglai Li Signed-off-by: Huacai Chen --- include/trace/events/kvm.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 74e40d5d4af4..fc7d0f8ff078 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -236,6 +236,41 @@ TRACE_EVENT(kvm_mmio, __entry->len, __entry->gpa, __entry->val) ); +#define KVM_TRACE_IOCSR_READ_UNSATISFIED 0 +#define KVM_TRACE_IOCSR_READ 1 +#define KVM_TRACE_IOCSR_WRITE 2 + +#define kvm_trace_symbol_iocsr \ + { KVM_TRACE_IOCSR_READ_UNSATISFIED, "unsatisfied-read" }, \ + { KVM_TRACE_IOCSR_READ, "read" }, \ + { KVM_TRACE_IOCSR_WRITE, "write" } + +TRACE_EVENT(kvm_iocsr, + TP_PROTO(int type, int len, u64 gpa, void *val), + TP_ARGS(type, len, gpa, val), + + TP_STRUCT__entry( + __field( u32, type ) + __field( u32, len ) + __field( u64, gpa ) + __field( u64, val ) + ), + + TP_fast_assign( + __entry->type = type; + __entry->len = len; + __entry->gpa = gpa; + __entry->val = 0; + if (val) + memcpy(&__entry->val, val, + min_t(u32, sizeof(__entry->val), len)); + ), + + TP_printk("iocsr %s len %u gpa 0x%llx val 0x%llx", + __print_symbolic(__entry->type, kvm_trace_symbol_iocsr), + __entry->len, __entry->gpa, __entry->val) +); + #define kvm_fpu_load_symbol \ {0, "unload"}, \ {1, "load"} -- cgit v1.2.3