[for-next][PATCH 00/10] tracing: More updates for 5.5

[for-next][PATCH 00/10] tracing: More updates for 5.5

[Steven Rostedt]

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
for-next

Head SHA1: 16c0f03f629a89e6a1249497202b2c154ff46206


Alexei Starovoitov (1):
      ftrace: Return ENOTSUPP when DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not configured

Divya Indi (2):
      tracing: Adding new functions for kernel access to Ftrace instances
      tracing: Sample module to demonstrate kernel access to Ftrace instances.

Enrico Weigelt, metux IT consult (1):
      ftrace: Use BIT() macro

Hassan Naveed (2):
      tracing: Use xarray for syscall trace events
      tracing: Enable syscall optimization for MIPS

Krzysztof Kozlowski (1):
      tracing: Fix Kconfig indentation

Steven Rostedt (VMware) (2):
      ftrace: Add a helper function to modify_ftrace_direct() to allow arch optimization
      ftrace: Rename ftrace_graph_stub to ftrace_stub_graph

Xianting Tian (1):
      ring-buffer: Fix typos in function ring_buffer_producer

----
 arch/Kconfig                         |   8 +++
 arch/mips/Kconfig                    |   1 +
 include/asm-generic/vmlinux.lds.h    |   8 +--
 include/linux/ftrace.h               |  63 +++++++++++------
 include/linux/trace.h                |   3 +-
 include/linux/trace_events.h         |   3 +-
 kernel/trace/Kconfig                 |   8 +--
 kernel/trace/fgraph.c                |   6 +-
 kernel/trace/ftrace.c                | 120 +++++++++++++++++++++++---------
 kernel/trace/ring_buffer_benchmark.c |   4 +-
 kernel/trace/trace.c                 |  96 +++++++++++++++++++------
 kernel/trace/trace.h                 |   1 -
 kernel/trace/trace_events.c          |  27 +++++++-
 kernel/trace/trace_syscalls.c        |  32 +++++++--
 samples/Kconfig                      |   7 ++
 samples/Makefile                     |   1 +
 samples/ftrace/Makefile              |   3 +
 samples/ftrace/sample-trace-array.c  | 131 +++++++++++++++++++++++++++++++++++
 samples/ftrace/sample-trace-array.h  |  84 ++++++++++++++++++++++
 19 files changed, 507 insertions(+), 99 deletions(-)
 create mode 100644 samples/ftrace/sample-trace-array.c
 create mode 100644 samples/ftrace/sample-trace-array.h

[for-next][PATCH 01/10] ftrace: Add a helper function to modify_ftrace_direct() to allow arch optimization

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

If a direct ftrace callback is at a location that does not have any other
ftrace helpers attached to it, it is possible to simply just change the
text to call the new caller (if the architecture supports it). But this
requires special architecture code. Currently, modify_ftrace_direct() uses a
trick to add a stub ftrace callback to the location forcing it to call the
ftrace iterator. Then it can change the direct helper to call the new
function in C, and then remove the stub. Removing the stub will have the
location now call the new location that the direct helper is using.

The new helper function does the registering the stub trick, but is a weak
function, allowing an architecture to override it to do something a bit more
direct.

Link: https://lore.kernel.org/r/20191115215125.mbqv7taqnx376yed@ast-mbp.dhcp.thefacebook.com

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  21 +++++++-
 kernel/trace/ftrace.c  | 120 ++++++++++++++++++++++++++++++-----------
 2 files changed, 107 insertions(+), 34 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 73eb2e93593f..dfaa37e1943d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -246,12 +246,24 @@ static inline void ftrace_free_init_mem(void) { }
 static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
+struct ftrace_func_entry {
+	struct hlist_node hlist;
+	unsigned long ip;
+	unsigned long direct; /* for direct lookup only */
+};
+
+struct dyn_ftrace;
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 extern int ftrace_direct_func_count;
 int register_ftrace_direct(unsigned long ip, unsigned long addr);
 int unregister_ftrace_direct(unsigned long ip, unsigned long addr);
 int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr);
 struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr);
+int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
+				struct dyn_ftrace *rec,
+				unsigned long old_addr,
+				unsigned long new_addr);
 #else
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)
@@ -271,6 +283,13 @@ static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long a
 {
 	return NULL;
 }
+static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
+					      struct dyn_ftrace *rec,
+					      unsigned long old_addr,
+					      unsigned long new_addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -343,8 +362,6 @@ static inline void stack_tracer_enable(void) { }
 int ftrace_arch_code_modify_prepare(void);
 int ftrace_arch_code_modify_post_process(void);
 
-struct dyn_ftrace;
-
 enum ftrace_bug_type {
 	FTRACE_BUG_UNKNOWN,
 	FTRACE_BUG_INIT,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ef79c8393f53..caae523f4ef3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1020,12 +1020,6 @@ static bool update_all_ops;
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
 
-struct ftrace_func_entry {
-	struct hlist_node hlist;
-	unsigned long ip;
-	unsigned long direct; /* for direct lookup only */
-};
-
 struct ftrace_func_probe {
 	struct ftrace_probe_ops	*probe_ops;
 	struct ftrace_ops	ops;
@@ -5112,7 +5106,8 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(register_ftrace_direct);
 
-static struct ftrace_func_entry *find_direct_entry(unsigned long *ip)
+static struct ftrace_func_entry *find_direct_entry(unsigned long *ip,
+						   struct dyn_ftrace **recp)
 {
 	struct ftrace_func_entry *entry;
 	struct dyn_ftrace *rec;
@@ -5132,6 +5127,9 @@ static struct ftrace_func_entry *find_direct_entry(unsigned long *ip)
 	/* Passed in ip just needs to be on the call site */
 	*ip = rec->ip;
 
+	if (recp)
+		*recp = rec;
+
 	return entry;
 }
 
@@ -5143,7 +5141,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 
 	mutex_lock(&direct_mutex);
 
-	entry = find_direct_entry(&ip);
+	entry = find_direct_entry(&ip, NULL);
 	if (!entry)
 		goto out_unlock;
 
@@ -5179,6 +5177,75 @@ static struct ftrace_ops stub_ops = {
 	.func		= ftrace_stub,
 };
 
+/**
+ * ftrace_modify_direct_caller - modify ftrace nop directly
+ * @entry: The ftrace hash entry of the direct helper for @rec
+ * @rec: The record representing the function site to patch
+ * @old_addr: The location that the site at @rec->ip currently calls
+ * @new_addr: The location that the site at @rec->ip should call
+ *
+ * An architecture may overwrite this function to optimize the
+ * changing of the direct callback on an ftrace nop location.
+ * This is called with the ftrace_lock mutex held, and no other
+ * ftrace callbacks are on the associated record (@rec). Thus,
+ * it is safe to modify the ftrace record, where it should be
+ * currently calling @old_addr directly, to call @new_addr.
+ *
+ * Safety checks should be made to make sure that the code at
+ * @rec->ip is currently calling @old_addr. And this must
+ * also update entry->direct to @new_addr.
+ */
+int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
+				       struct dyn_ftrace *rec,
+				       unsigned long old_addr,
+				       unsigned long new_addr)
+{
+	unsigned long ip = rec->ip;
+	int ret;
+
+	/*
+	 * The ftrace_lock was used to determine if the record
+	 * had more than one registered user to it. If it did,
+	 * we needed to prevent that from changing to do the quick
+	 * switch. But if it did not (only a direct caller was attached)
+	 * then this function is called. But this function can deal
+	 * with attached callers to the rec that we care about, and
+	 * since this function uses standard ftrace calls that take
+	 * the ftrace_lock mutex, we need to release it.
+	 */
+	mutex_unlock(&ftrace_lock);
+
+	/*
+	 * By setting a stub function at the same address, we force
+	 * the code to call the iterator and the direct_ops helper.
+	 * This means that @ip does not call the direct call, and
+	 * we can simply modify it.
+	 */
+	ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0);
+	if (ret)
+		goto out_lock;
+
+	ret = register_ftrace_function(&stub_ops);
+	if (ret) {
+		ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
+		goto out_lock;
+	}
+
+	entry->direct = new_addr;
+
+	/*
+	 * By removing the stub, we put back the direct call, calling
+	 * the @new_addr.
+	 */
+	unregister_ftrace_function(&stub_ops);
+	ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
+
+ out_lock:
+	mutex_lock(&ftrace_lock);
+
+	return ret;
+}
+
 /**
  * modify_ftrace_direct - Modify an existing direct call to call something else
  * @ip: The instruction pointer to modify
@@ -5197,11 +5264,13 @@ int modify_ftrace_direct(unsigned long ip,
 			 unsigned long old_addr, unsigned long new_addr)
 {
 	struct ftrace_func_entry *entry;
+	struct dyn_ftrace *rec;
 	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
 
-	entry = find_direct_entry(&ip);
+	mutex_lock(&ftrace_lock);
+	entry = find_direct_entry(&ip, &rec);
 	if (!entry)
 		goto out_unlock;
 
@@ -5210,33 +5279,20 @@ int modify_ftrace_direct(unsigned long ip,
 		goto out_unlock;
 
 	/*
-	 * By setting a stub function at the same address, we force
-	 * the code to call the iterator and the direct_ops helper.
-	 * This means that @ip does not call the direct call, and
-	 * we can simply modify it.
+	 * If there's no other ftrace callback on the rec->ip location,
+	 * then it can be changed directly by the architecture.
+	 * If there is another caller, then we just need to change the
+	 * direct caller helper to point to @new_addr.
 	 */
-	ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0);
-	if (ret)
-		goto out_unlock;
-
-	ret = register_ftrace_function(&stub_ops);
-	if (ret) {
-		ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
-		goto out_unlock;
+	if (ftrace_rec_count(rec) == 1) {
+		ret = ftrace_modify_direct_caller(entry, rec, old_addr, new_addr);
+	} else {
+		entry->direct = new_addr;
+		ret = 0;
 	}
 
-	entry->direct = new_addr;
-
-	/*
-	 * By removing the stub, we put back the direct call, calling
-	 * the @new_addr.
-	 */
-	unregister_ftrace_function(&stub_ops);
-	ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
-
-	ret = 0;
-
  out_unlock:
+	mutex_unlock(&ftrace_lock);
 	mutex_unlock(&direct_mutex);
 	return ret;
 }
-- 
2.24.0

[for-next][PATCH 02/10] ftrace: Rename ftrace_graph_stub to ftrace_stub_graph

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

The ftrace_graph_stub was created and points to ftrace_stub as a way to
assign the functon graph tracer function pointer to a stub function with a
different prototype than what ftrace_stub has and not trigger the C
verifier. The ftrace_graph_stub was created via the linker script
vmlinux.lds.h. Unfortunately, powerpc already uses the name
ftrace_graph_stub for its internal implementation of the function graph
tracer, and even though powerpc would still build, the change via the linker
script broke function tracer on powerpc from working.

By using the name ftrace_stub_graph, which does not exist anywhere else in
the kernel, this should not be a problem.

Link: https://lore.kernel.org/r/1573849732.5937.136.camel@lca.pw

Fixes: b83b43ffc6e4 ("fgraph: Fix function type mismatches of ftrace_graph_return using ftrace_stub")
Reorted-by: Qian Cai <cai@lca.pw>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/asm-generic/vmlinux.lds.h | 8 ++++----
 kernel/trace/fgraph.c             | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0f358be551cd..996db32c491b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -112,7 +112,7 @@
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 #ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
 /*
- * Need to also make ftrace_graph_stub point to ftrace_stub
+ * Need to also make ftrace_stub_graph point to ftrace_stub
  * so that the same stub location may have different protocols
  * and not mess up with C verifiers.
  */
@@ -120,17 +120,17 @@
 			__start_mcount_loc = .;			\
 			KEEP(*(__patchable_function_entries))	\
 			__stop_mcount_loc = .;			\
-			ftrace_graph_stub = ftrace_stub;
+			ftrace_stub_graph = ftrace_stub;
 #else
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
 			__stop_mcount_loc = .;			\
-			ftrace_graph_stub = ftrace_stub;
+			ftrace_stub_graph = ftrace_stub;
 #endif
 #else
 # ifdef CONFIG_FUNCTION_TRACER
-#  define MCOUNT_REC()	ftrace_graph_stub = ftrace_stub;
+#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;
 # else
 #  define MCOUNT_REC()
 # endif
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index fa3ce10d0405..67e0c462b059 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -336,10 +336,10 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
  * Simply points to ftrace_stub, but with the proper protocol.
  * Defined by the linker script in linux/vmlinux.lds.h
  */
-extern void ftrace_graph_stub(struct ftrace_graph_ret *);
+extern void ftrace_stub_graph(struct ftrace_graph_ret *);
 
 /* The callbacks that hook a function */
-trace_func_graph_ret_t ftrace_graph_return = ftrace_graph_stub;
+trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph;
 trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
 static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
@@ -619,7 +619,7 @@ void unregister_ftrace_graph(struct fgraph_ops *gops)
 		goto out;
 
 	ftrace_graph_active--;
-	ftrace_graph_return = ftrace_graph_stub;
+	ftrace_graph_return = ftrace_stub_graph;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	__ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
-- 
2.24.0

[for-next][PATCH 03/10] ftrace: Return ENOTSUPP when DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not configured

[Steven Rostedt]

From: Alexei Starovoitov <alexei.starovoitov@gmail.com>

When CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not set it's best to
have the stub functions return ENOTSUPP instead of ENODEV,
otherwise ENODEV is a valid error when ip is incorrect which is
indistinguishable from ftrace not compiled in.

Link: http://lkml.kernel.org/r/CAADnVQ+OzTikM9EhrfsC7NFsVYhATW1SVHxK64w3xn9qpk81pg@mail.gmail.com

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dfaa37e1943d..af79b0f8cdc1 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -268,16 +268,16 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)
 {
-	return -ENODEV;
+	return -ENOTSUPP;
 }
 static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 {
-	return -ENODEV;
+	return -ENOTSUPP;
 }
 static inline int modify_ftrace_direct(unsigned long ip,
 				       unsigned long old_addr, unsigned long new_addr)
 {
-	return -ENODEV;
+	return -ENOTSUPP;
 }
 static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr)
 {
-- 
2.24.0

[for-next][PATCH 04/10] ftrace: Use BIT() macro

[Steven Rostedt]

From: "Enrico Weigelt, metux IT consult" <info@metux.net>

It's cleaner to use the BIT() macro instead of raw shift operation.

Link: http://lkml.kernel.org/r/20191121133815.15040-1-info@metux.net

Signed-off-by: Enrico Weigelt, metux IT consult <info@metux.net>
[ Added BIT() for bits 16 and 17 ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index af79b0f8cdc1..232806d5689d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -149,24 +149,24 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            (internal ftrace only, should not be used by others)
  */
 enum {
-	FTRACE_OPS_FL_ENABLED			= 1 << 0,
-	FTRACE_OPS_FL_DYNAMIC			= 1 << 1,
-	FTRACE_OPS_FL_SAVE_REGS			= 1 << 2,
-	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 3,
-	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 4,
-	FTRACE_OPS_FL_STUB			= 1 << 5,
-	FTRACE_OPS_FL_INITIALIZED		= 1 << 6,
-	FTRACE_OPS_FL_DELETED			= 1 << 7,
-	FTRACE_OPS_FL_ADDING			= 1 << 8,
-	FTRACE_OPS_FL_REMOVING			= 1 << 9,
-	FTRACE_OPS_FL_MODIFYING			= 1 << 10,
-	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 11,
-	FTRACE_OPS_FL_IPMODIFY			= 1 << 12,
-	FTRACE_OPS_FL_PID			= 1 << 13,
-	FTRACE_OPS_FL_RCU			= 1 << 14,
-	FTRACE_OPS_FL_TRACE_ARRAY		= 1 << 15,
-	FTRACE_OPS_FL_PERMANENT                 = 1 << 16,
-	FTRACE_OPS_FL_DIRECT			= 1 << 17,
+	FTRACE_OPS_FL_ENABLED			= BIT(0),
+	FTRACE_OPS_FL_DYNAMIC			= BIT(1),
+	FTRACE_OPS_FL_SAVE_REGS			= BIT(2),
+	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= BIT(3),
+	FTRACE_OPS_FL_RECURSION_SAFE		= BIT(4),
+	FTRACE_OPS_FL_STUB			= BIT(5),
+	FTRACE_OPS_FL_INITIALIZED		= BIT(6),
+	FTRACE_OPS_FL_DELETED			= BIT(7),
+	FTRACE_OPS_FL_ADDING			= BIT(8),
+	FTRACE_OPS_FL_REMOVING			= BIT(9),
+	FTRACE_OPS_FL_MODIFYING			= BIT(10),
+	FTRACE_OPS_FL_ALLOC_TRAMP		= BIT(11),
+	FTRACE_OPS_FL_IPMODIFY			= BIT(12),
+	FTRACE_OPS_FL_PID			= BIT(13),
+	FTRACE_OPS_FL_RCU			= BIT(14),
+	FTRACE_OPS_FL_TRACE_ARRAY		= BIT(15),
+	FTRACE_OPS_FL_PERMANENT                 = BIT(16),
+	FTRACE_OPS_FL_DIRECT			= BIT(17),
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-- 
2.24.0

[for-next][PATCH 05/10] ring-buffer: Fix typos in function ring_buffer_producer

[Steven Rostedt]

From: Xianting Tian <xianting_tian@126.com>

Fix spelling and other typos

Link: http://lkml.kernel.org/r/1573916755-32478-1-git-send-email-xianting_tian@126.com

Signed-off-by: Xianting Tian <xianting_tian@126.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer_benchmark.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 09b0b49f346e..32149e46551c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -269,10 +269,10 @@ static void ring_buffer_producer(void)
 
 #ifndef CONFIG_PREEMPTION
 		/*
-		 * If we are a non preempt kernel, the 10 second run will
+		 * If we are a non preempt kernel, the 10 seconds run will
 		 * stop everything while it runs. Instead, we will call
 		 * cond_resched and also add any time that was lost by a
-		 * rescedule.
+		 * reschedule.
 		 *
 		 * Do a cond resched at the same frequency we would wake up
 		 * the reader.
-- 
2.24.0

[for-next][PATCH 06/10] tracing: Fix Kconfig indentation

[Steven Rostedt]

From: Krzysztof Kozlowski <krzk@kernel.org>

Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
	$ sed -e 's/^        /\t/' -i */Kconfig

Link: http://lkml.kernel.org/r/20191120133807.12741-1-krzk@kernel.org

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/Kconfig | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b872716bb2a0..f67620499faa 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -79,7 +79,7 @@ config FTRACE_NMI_ENTER
 
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
-        select GLOB
+	select GLOB
 	bool
 
 config CONTEXT_SWITCH_TRACER
@@ -311,7 +311,7 @@ config TRACER_SNAPSHOT
 	      cat snapshot
 
 config TRACER_SNAPSHOT_PER_CPU_SWAP
-        bool "Allow snapshot to swap per CPU"
+	bool "Allow snapshot to swap per CPU"
 	depends on TRACER_SNAPSHOT
 	select RING_BUFFER_ALLOW_SWAP
 	help
@@ -683,7 +683,7 @@ config MMIOTRACE_TEST
 	  Say N, unless you absolutely know what you are doing.
 
 config TRACEPOINT_BENCHMARK
-        bool "Add tracepoint that benchmarks tracepoints"
+	bool "Add tracepoint that benchmarks tracepoints"
 	help
 	 This option creates the tracepoint "benchmark:benchmark_event".
 	 When the tracepoint is enabled, it kicks off a kernel thread that
@@ -732,7 +732,7 @@ config RING_BUFFER_STARTUP_TEST
        bool "Ring buffer startup self test"
        depends on RING_BUFFER
        help
-         Run a simple self test on the ring buffer on boot up. Late in the
+	 Run a simple self test on the ring buffer on boot up. Late in the
 	 kernel boot sequence, the test will start that kicks off
 	 a thread per cpu. Each thread will write various size events
 	 into the ring buffer. Another thread is created to send IPIs
-- 
2.24.0

[for-next][PATCH 07/10] tracing: Adding new functions for kernel access to Ftrace instances

[Steven Rostedt]

From: Divya Indi <divya.indi@oracle.com>

Adding 2 new functions -
1) struct trace_array *trace_array_get_by_name(const char *name);

Return pointer to a trace array with given name. If it does not exist,
create and return pointer to the new trace array.

2) int trace_array_set_clr_event(struct trace_array *tr,
const char *system ,const char *event, bool enable);

Enable/Disable events to this trace array.

Additionally,
- To handle reference counters, export trace_array_put()
- Due to introduction of the above 2 new functions, we no longer need to
  export - ftrace_set_clr_event & trace_array_create APIs.

Link: http://lkml.kernel.org/r/1574276919-11119-2-git-send-email-divya.indi@oracle.com

Signed-off-by: Divya Indi <divya.indi@oracle.com>
Reviewed-by: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace.h        |  3 +-
 include/linux/trace_events.h |  3 +-
 kernel/trace/trace.c         | 96 ++++++++++++++++++++++++++++--------
 kernel/trace/trace.h         |  1 -
 kernel/trace/trace_events.c  | 27 +++++++++-
 5 files changed, 106 insertions(+), 24 deletions(-)

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 24fcf07812ae..7fd86d3c691f 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -29,7 +29,8 @@ struct trace_array;
 void trace_printk_init_buffers(void);
 int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		const char *fmt, ...);
-struct trace_array *trace_array_create(const char *name);
+void trace_array_put(struct trace_array *tr);
+struct trace_array *trace_array_get_by_name(const char *name);
 int trace_array_destroy(struct trace_array *tr);
 #endif	/* CONFIG_TRACING */
 
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 60a41b7069dd..4c6e15605766 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -555,7 +555,8 @@ extern int trace_event_get_offsets(struct trace_event_call *call);
 
 int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
 int trace_set_clr_event(const char *system, const char *event, int set);
-
+int trace_array_set_clr_event(struct trace_array *tr, const char *system,
+		const char *event, bool enable);
 /*
  * The double __builtin_constant_p is because gcc will give us an error
  * if we try to allocate the static variable to fmt if it is not a
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 42659ce6ac0c..02a23a6e5e00 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -301,12 +301,24 @@ static void __trace_array_put(struct trace_array *this_tr)
 	this_tr->ref--;
 }
 
+/**
+ * trace_array_put - Decrement the reference counter for this trace array.
+ *
+ * NOTE: Use this when we no longer need the trace array returned by
+ * trace_array_get_by_name(). This ensures the trace array can be later
+ * destroyed.
+ *
+ */
 void trace_array_put(struct trace_array *this_tr)
 {
+	if (!this_tr)
+		return;
+
 	mutex_lock(&trace_types_lock);
 	__trace_array_put(this_tr);
 	mutex_unlock(&trace_types_lock);
 }
+EXPORT_SYMBOL_GPL(trace_array_put);
 
 int tracing_check_open_get_tr(struct trace_array *tr)
 {
@@ -8437,24 +8449,15 @@ static void update_tracer_options(struct trace_array *tr)
 	mutex_unlock(&trace_types_lock);
 }
 
-struct trace_array *trace_array_create(const char *name)
+static struct trace_array *trace_array_create(const char *name)
 {
 	struct trace_array *tr;
 	int ret;
 
-	mutex_lock(&event_mutex);
-	mutex_lock(&trace_types_lock);
-
-	ret = -EEXIST;
-	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
-		if (tr->name && strcmp(tr->name, name) == 0)
-			goto out_unlock;
-	}
-
 	ret = -ENOMEM;
 	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
 	if (!tr)
-		goto out_unlock;
+		return ERR_PTR(ret);
 
 	tr->name = kstrdup(name, GFP_KERNEL);
 	if (!tr->name)
@@ -8499,8 +8502,8 @@ struct trace_array *trace_array_create(const char *name)
 
 	list_add(&tr->list, &ftrace_trace_arrays);
 
-	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
+	tr->ref++;
+
 
 	return tr;
 
@@ -8510,24 +8513,77 @@ struct trace_array *trace_array_create(const char *name)
 	kfree(tr->name);
 	kfree(tr);
 
- out_unlock:
-	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
-
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(trace_array_create);
 
 static int instance_mkdir(const char *name)
 {
-	return PTR_ERR_OR_ZERO(trace_array_create(name));
+	struct trace_array *tr;
+	int ret;
+
+	mutex_lock(&event_mutex);
+	mutex_lock(&trace_types_lock);
+
+	ret = -EEXIST;
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0)
+			goto out_unlock;
+	}
+
+	tr = trace_array_create(name);
+
+	ret = PTR_ERR_OR_ZERO(tr);
+
+out_unlock:
+	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
+	return ret;
+}
+
+/**
+ * trace_array_get_by_name - Create/Lookup a trace array, given its name.
+ * @name: The name of the trace array to be looked up/created.
+ *
+ * Returns pointer to trace array with given name.
+ * NULL, if it cannot be created.
+ *
+ * NOTE: This function increments the reference counter associated with the
+ * trace array returned. This makes sure it cannot be freed while in use.
+ * Use trace_array_put() once the trace array is no longer needed.
+ *
+ */
+struct trace_array *trace_array_get_by_name(const char *name)
+{
+	struct trace_array *tr;
+
+	mutex_lock(&event_mutex);
+	mutex_lock(&trace_types_lock);
+
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0)
+			goto out_unlock;
+	}
+
+	tr = trace_array_create(name);
+
+	if (IS_ERR(tr))
+		tr = NULL;
+out_unlock:
+	if (tr)
+		tr->ref++;
+
+	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
+	return tr;
 }
+EXPORT_SYMBOL_GPL(trace_array_get_by_name);
 
 static int __remove_instance(struct trace_array *tr)
 {
 	int i;
 
-	if (tr->ref || (tr->current_trace && tr->current_trace->ref))
+	/* Reference counter for a newly created trace array = 1. */
+	if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref))
 		return -EBUSY;
 
 	list_del(&tr->list);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2df8aed6a8f0..ca7fccafbcbb 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -345,7 +345,6 @@ extern struct list_head ftrace_trace_arrays;
 extern struct mutex trace_types_lock;
 
 extern int trace_array_get(struct trace_array *tr);
-extern void trace_array_put(struct trace_array *tr);
 extern int tracing_check_open_get_tr(struct trace_array *tr);
 
 extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2a3ac2365445..6b3a69e9aa6a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -827,7 +827,6 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(ftrace_set_clr_event);
 
 /**
  * trace_set_clr_event - enable or disable an event
@@ -852,6 +851,32 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 }
 EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
+/**
+ * trace_array_set_clr_event - enable or disable an event for a trace array.
+ * @tr: concerned trace array.
+ * @system: system name to match (NULL for any system)
+ * @event: event name to match (NULL for all events, within system)
+ * @enable: true to enable, false to disable
+ *
+ * This is a way for other parts of the kernel to enable or disable
+ * event recording.
+ *
+ * Returns 0 on success, -EINVAL if the parameters do not match any
+ * registered events.
+ */
+int trace_array_set_clr_event(struct trace_array *tr, const char *system,
+		const char *event, bool enable)
+{
+	int set;
+
+	if (!tr)
+		return -ENOENT;
+
+	set = (enable == true) ? 1 : 0;
+	return __ftrace_set_clr_event(tr, NULL, system, event, set);
+}
+EXPORT_SYMBOL_GPL(trace_array_set_clr_event);
+
 /* 128 should be much more than enough */
 #define EVENT_BUF_SIZE		127
 
-- 
2.24.0

[for-next][PATCH 08/10] tracing: Sample module to demonstrate kernel access to Ftrace instances.

[Steven Rostedt]

From: Divya Indi <divya.indi@oracle.com>

This is a sample module to demonstrate the use of the newly introduced and
exported APIs to access Ftrace instances from within the kernel.

Newly introduced APIs used here -

1. Create/Lookup a trace array with the given name.
struct trace_array *trace_array_get_by_name(const char *name)

2. Destroy/Remove a trace array.
int trace_array_destroy(struct trace_array *tr)

4. Enable/Disable trace events:
int trace_array_set_clr_event(struct trace_array *tr, const char *system,
        const char *event, bool enable);

Exported APIs -
1. trace_printk equivalent for instances.
int trace_array_printk(struct trace_array *tr,
               unsigned long ip, const char *fmt, ...);

2. Helper function.
void trace_printk_init_buffers(void);

3. To decrement the reference counter.
void trace_array_put(struct trace_array *tr)

Sample output(contents of /sys/kernel/tracing/instances/sample-instance)
NOTE: Tracing disabled after ~5 sec)

                              _-----=> irqs-off
                             / _----=> need-resched
                            | / _---=> hardirq/softirq
                            || / _--=> preempt-depth
                            ||| /     delay
           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
              | |       |   ||||       |         |
sample-instance-1452  [002] ....    49.430948: simple_thread: trace_array_printk: count=0
sample-instance-1452  [002] ....    49.430951: sample_event: count value=0 at jiffies=4294716608
sample-instance-1452  [002] ....    50.454847: simple_thread: trace_array_printk: count=1
sample-instance-1452  [002] ....    50.454849: sample_event: count value=1 at jiffies=4294717632
sample-instance-1452  [002] ....    51.478748: simple_thread: trace_array_printk: count=2
sample-instance-1452  [002] ....    51.478750: sample_event: count value=2 at jiffies=4294718656
sample-instance-1452  [002] ....    52.502652: simple_thread: trace_array_printk: count=3
sample-instance-1452  [002] ....    52.502655: sample_event: count value=3 at jiffies=4294719680
sample-instance-1452  [002] ....    53.526533: simple_thread: trace_array_printk: count=4
sample-instance-1452  [002] ....    53.526535: sample_event: count value=4 at jiffies=4294720704
sample-instance-1452  [002] ....    54.550438: simple_thread: trace_array_printk: count=5
sample-instance-1452  [002] ....    55.574336: simple_thread: trace_array_printk: count=6

Link: http://lkml.kernel.org/r/1574276919-11119-3-git-send-email-divya.indi@oracle.com

Reviewed-by: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>
Signed-off-by: Divya Indi <divya.indi@oracle.com>
[ Moved to samples/ftrace ]
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 samples/Kconfig                     |   7 ++
 samples/Makefile                    |   1 +
 samples/ftrace/Makefile             |   3 +
 samples/ftrace/sample-trace-array.c | 131 ++++++++++++++++++++++++++++
 samples/ftrace/sample-trace-array.h |  84 ++++++++++++++++++
 5 files changed, 226 insertions(+)
 create mode 100644 samples/ftrace/sample-trace-array.c
 create mode 100644 samples/ftrace/sample-trace-array.h

diff --git a/samples/Kconfig b/samples/Kconfig
index 65b5967dac0c..ad64b223f3d0 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -27,6 +27,13 @@ config SAMPLE_FTRACE_DIRECT
 	  This builds an ftrace direct function example
 	  that hooks to wake_up_process and prints the parameters.
 
+config SAMPLE_TRACE_ARRAY
+        tristate "Build sample module for kernel access to Ftrace instancess"
+	depends on EVENT_TRACING && m
+	help
+	 This builds a module that demonstrates the use of various APIs to
+	 access Ftrace instances from within the kernel.
+
 config SAMPLE_KOBJECT
 	tristate "Build kobject examples"
 	help
diff --git a/samples/Makefile b/samples/Makefile
index cd496d633370..297f8934773f 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -18,6 +18,7 @@ subdir-$(CONFIG_SAMPLE_SECCOMP)		+= seccomp
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS)	+= trace_events/
 obj-$(CONFIG_SAMPLE_TRACE_PRINTK)	+= trace_printk/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT)	+= ftrace/
+obj-$(CONFIG_SAMPLE_TRACE_ARRAY)	+= ftrace/
 obj-$(CONFIG_VIDEO_PCI_SKELETON)	+= v4l/
 obj-y					+= vfio-mdev/
 subdir-$(CONFIG_SAMPLE_VFS)		+= vfs
diff --git a/samples/ftrace/Makefile b/samples/ftrace/Makefile
index fb0c3ae18295..4ce896e10b2e 100644
--- a/samples/ftrace/Makefile
+++ b/samples/ftrace/Makefile
@@ -3,3 +3,6 @@
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
+
+CFLAGS_sample-trace-array.o := -I$(src)
+obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
new file mode 100644
index 000000000000..d523450d73eb
--- /dev/null
+++ b/samples/ftrace/sample-trace-array.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/trace.h>
+#include <linux/trace_events.h>
+#include <linux/timer.h>
+#include <linux/err.h>
+#include <linux/jiffies.h>
+
+/*
+ * Any file that uses trace points, must include the header.
+ * But only one file, must include the header by defining
+ * CREATE_TRACE_POINTS first.  This will make the C code that
+ * creates the handles for the trace points.
+ */
+#define CREATE_TRACE_POINTS
+#include "sample-trace-array.h"
+
+struct trace_array *tr;
+static void mytimer_handler(struct timer_list *unused);
+static struct task_struct *simple_tsk;
+
+/*
+ * mytimer: Timer setup to disable tracing for event "sample_event". This
+ * timer is only for the purposes of the sample module to demonstrate access of
+ * Ftrace instances from within kernel.
+ */
+static DEFINE_TIMER(mytimer, mytimer_handler);
+
+static void mytimer_handler(struct timer_list *unused)
+{
+	/*
+	 * Disable tracing for event "sample_event".
+	 */
+	trace_array_set_clr_event(tr, "sample-subsystem", "sample_event",
+			false);
+}
+
+static void simple_thread_func(int count)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(HZ);
+
+	/*
+	 * Printing count value using trace_array_printk() - trace_printk()
+	 * equivalent for the instance buffers.
+	 */
+	trace_array_printk(tr, _THIS_IP_, "trace_array_printk: count=%d\n",
+			count);
+	/*
+	 * Tracepoint for event "sample_event". This will print the
+	 * current value of count and current jiffies.
+	 */
+	trace_sample_event(count, jiffies);
+}
+
+static int simple_thread(void *arg)
+{
+	int count = 0;
+	unsigned long delay = msecs_to_jiffies(5000);
+
+	/*
+	 * Enable tracing for "sample_event".
+	 */
+	trace_array_set_clr_event(tr, "sample-subsystem", "sample_event", true);
+
+	/*
+	 * Adding timer - mytimer. This timer will disable tracing after
+	 * delay seconds.
+	 *
+	 */
+	add_timer(&mytimer);
+	mod_timer(&mytimer, jiffies+delay);
+
+	while (!kthread_should_stop())
+		simple_thread_func(count++);
+
+	del_timer(&mytimer);
+
+	/*
+	 * trace_array_put() decrements the reference counter associated with
+	 * the trace array - "tr". We are done using the trace array, hence
+	 * decrement the reference counter so that it can be destroyed using
+	 * trace_array_destroy().
+	 */
+	trace_array_put(tr);
+
+	return 0;
+}
+
+static int __init sample_trace_array_init(void)
+{
+	/*
+	 * Return a pointer to the trace array with name "sample-instance" if it
+	 * exists, else create a new trace array.
+	 *
+	 * NOTE: This function increments the reference counter
+	 * associated with the trace array - "tr".
+	 */
+	tr = trace_array_get_by_name("sample-instance");
+
+	if (!tr)
+		return -1;
+	/*
+	 * If context specific per-cpu buffers havent already been allocated.
+	 */
+	trace_printk_init_buffers();
+
+	simple_tsk = kthread_run(simple_thread, NULL, "sample-instance");
+	if (IS_ERR(simple_tsk))
+		return -1;
+	return 0;
+}
+
+static void __exit sample_trace_array_exit(void)
+{
+	kthread_stop(simple_tsk);
+
+	/*
+	 * We are unloading our module and no longer require the trace array.
+	 * Remove/destroy "tr" using trace_array_destroy()
+	 */
+	trace_array_destroy(tr);
+}
+
+module_init(sample_trace_array_init);
+module_exit(sample_trace_array_exit);
+
+MODULE_AUTHOR("Divya Indi");
+MODULE_DESCRIPTION("Sample module for kernel access to Ftrace instances");
+MODULE_LICENSE("GPL");
diff --git a/samples/ftrace/sample-trace-array.h b/samples/ftrace/sample-trace-array.h
new file mode 100644
index 000000000000..6f8962428158
--- /dev/null
+++ b/samples/ftrace/sample-trace-array.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * If TRACE_SYSTEM is defined, that will be the directory created
+ * in the ftrace directory under /sys/kernel/tracing/events/<system>
+ *
+ * The define_trace.h below will also look for a file name of
+ * TRACE_SYSTEM.h where TRACE_SYSTEM is what is defined here.
+ * In this case, it would look for sample-trace.h
+ *
+ * If the header name will be different than the system name
+ * (as in this case), then you can override the header name that
+ * define_trace.h will look up by defining TRACE_INCLUDE_FILE
+ *
+ * This file is called sample-trace-array.h but we want the system
+ * to be called "sample-subsystem". Therefore we must define the name of this
+ * file:
+ *
+ * #define TRACE_INCLUDE_FILE sample-trace-array
+ *
+ * As we do in the bottom of this file.
+ *
+ * Notice that TRACE_SYSTEM should be defined outside of #if
+ * protection, just like TRACE_INCLUDE_FILE.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sample-subsystem
+
+/*
+ * TRACE_SYSTEM is expected to be a C valid variable (alpha-numeric
+ * and underscore), although it may start with numbers. If for some
+ * reason it is not, you need to add the following lines:
+ */
+#undef TRACE_SYSTEM_VAR
+#define TRACE_SYSTEM_VAR sample_subsystem
+
+/*
+ * But the above is only needed if TRACE_SYSTEM is not alpha-numeric
+ * and underscored. By default, TRACE_SYSTEM_VAR will be equal to
+ * TRACE_SYSTEM. As TRACE_SYSTEM_VAR must be alpha-numeric, if
+ * TRACE_SYSTEM is not, then TRACE_SYSTEM_VAR must be defined with
+ * only alpha-numeric and underscores.
+ *
+ * The TRACE_SYSTEM_VAR is only used internally and not visible to
+ * user space.
+ */
+
+/*
+ * Notice that this file is not protected like a normal header.
+ * We also must allow for rereading of this file. The
+ *
+ *  || defined(TRACE_HEADER_MULTI_READ)
+ *
+ * serves this purpose.
+ */
+#if !defined(_SAMPLE_TRACE_ARRAY_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _SAMPLE_TRACE_ARRAY_H
+
+#include <linux/tracepoint.h>
+TRACE_EVENT(sample_event,
+
+	TP_PROTO(int count, unsigned long time),
+
+	TP_ARGS(count, time),
+
+	TP_STRUCT__entry(
+		__field(int, count)
+		__field(unsigned long, time)
+	),
+
+	TP_fast_assign(
+		__entry->count = count;
+		__entry->time = time;
+	),
+
+	TP_printk("count value=%d at jiffies=%lu", __entry->count,
+		__entry->time)
+	);
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE sample-trace-array
+#include <trace/define_trace.h>
-- 
2.24.0

[for-next][PATCH 09/10] tracing: Use xarray for syscall trace events

[Steven Rostedt]

From: Hassan Naveed <hnaveed@wavecomp.com>

Currently, a lot of memory is wasted for architectures like MIPS when
init_ftrace_syscalls() allocates the array for syscalls using kcalloc.
This is because syscalls numbers start from 4000, 5000 or 6000 and
array elements up to that point are unused.
Fix this by using a data structure more suited to storing sparsely
populated arrays. The XARRAY data structure, implemented using radix
trees, is much more memory efficient for storing the syscalls in
question.

Link: http://lkml.kernel.org/r/20191115234314.21599-1-hnaveed@wavecomp.com

Signed-off-by: Hassan Naveed <hnaveed@wavecomp.com>
Reviewed-by: Paul Burton <paulburton@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/Kconfig                  |  8 ++++++++
 kernel/trace/trace_syscalls.c | 32 +++++++++++++++++++++++++-------
 2 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 5f8a5d84dbbe..69c87e8608d8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -960,6 +960,14 @@ config RELR
 config ARCH_HAS_MEM_ENCRYPT
 	bool
 
+config HAVE_SPARSE_SYSCALL_NR
+       bool
+       help
+          An architecture should select this if its syscall numbering is sparse
+	  to save space. For example, MIPS architecture has a syscall array with
+	  entries at 4000, 5000 and 6000 locations. This option turns on syscall
+	  related optimizations for a given architecture.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index fa8fbff736d6..16fa218556fa 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
 #include <linux/ftrace.h>
 #include <linux/perf_event.h>
+#include <linux/xarray.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
@@ -30,6 +31,7 @@ syscall_get_enter_fields(struct trace_event_call *call)
 extern struct syscall_metadata *__start_syscalls_metadata[];
 extern struct syscall_metadata *__stop_syscalls_metadata[];
 
+static DEFINE_XARRAY(syscalls_metadata_sparse);
 static struct syscall_metadata **syscalls_metadata;
 
 #ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
@@ -101,6 +103,9 @@ find_syscall_meta(unsigned long syscall)
 
 static struct syscall_metadata *syscall_nr_to_meta(int nr)
 {
+	if (IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR))
+		return xa_load(&syscalls_metadata_sparse, (unsigned long)nr);
+
 	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
 		return NULL;
 
@@ -536,12 +541,16 @@ void __init init_ftrace_syscalls(void)
 	struct syscall_metadata *meta;
 	unsigned long addr;
 	int i;
-
-	syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
-				    GFP_KERNEL);
-	if (!syscalls_metadata) {
-		WARN_ON(1);
-		return;
+	void *ret;
+
+	if (!IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR)) {
+		syscalls_metadata = kcalloc(NR_syscalls,
+					sizeof(*syscalls_metadata),
+					GFP_KERNEL);
+		if (!syscalls_metadata) {
+			WARN_ON(1);
+			return;
+		}
 	}
 
 	for (i = 0; i < NR_syscalls; i++) {
@@ -551,7 +560,16 @@ void __init init_ftrace_syscalls(void)
 			continue;
 
 		meta->syscall_nr = i;
-		syscalls_metadata[i] = meta;
+
+		if (!IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR)) {
+			syscalls_metadata[i] = meta;
+		} else {
+			ret = xa_store(&syscalls_metadata_sparse, i, meta,
+					GFP_KERNEL);
+			WARN(xa_is_err(ret),
+				"Syscall memory allocation failed\n");
+		}
+
 	}
 }
 
-- 
2.24.0

[for-next][PATCH 10/10] tracing: Enable syscall optimization for MIPS

[Steven Rostedt]

From: Hassan Naveed <hnaveed@wavecomp.com>

Since MIPS architecture has a sparse syscall array, select the
HAVE_SPARSE_SYSCALL_NR to save space.

Link: http://lkml.kernel.org/r/20191115234314.21599-2-hnaveed@wavecomp.com

Signed-off-by: Hassan Naveed <hnaveed@wavecomp.com>
Reviewed-by: Paul Burton <paulburton@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/mips/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a0bd9bdb5f83..c7f59c4a00d8 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -73,6 +73,7 @@ config MIPS
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
+	select HAVE_SPARSE_SYSCALL_NR
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP
-- 
2.24.0