Merge tag 'trace-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "The biggest change here is the updates to kprobes

  Back in January I posted patches to create function based events.
  These were the events that you suggested I make to allow developers to
  easily create events in code where no trace event exists. After
  posting those changes for review, it was suggested that we implement
  this instead with kprobes.

  The problem with kprobes is that the interface is too complex and
  needs to be simplified. Masami Hiramatsu posted patches in March and
  I've been playing with them a bit. There's been a bit of clean up in
  the kprobe code that was inspired by the function based event patches,
  and a couple of enhancements to the kprobe event interface.

   - If the arch supports it (we added support for x86), you can place a
     kprobe event at the start of a function and use $arg1, $arg2, etc
     to reference the arguments of a function. (Before you needed to
     know what register or where on the stack the argument was).

   - The second is a way to see array of events. For example, if you
     reference a mac address, you can add:

	echo 'p:mac ip_rcv perm_addr=+574($arg2):x8[6]' > kprobe_events

     And this will produce:

	mac: (ip_rcv+0x0/0x140) perm_addr={0x52,0x54,0x0,0xc0,0x76,0xec}

  Other changes include

   - Exporting trace_dump_stack to modules

   - Have the stack tracer trace the entire stack (stop trying to remove
     tracing itself, as we keep removing too much).

   - Added support for SDT in uprobes"

[ SDT - "Statically Defined Tracing" are userspace markers for tracing.
  Let's not use random TLA's in explanations unless they are fairly
  well-established as generic (at least for kernel people) - Linus ]

* tag 'trace-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (24 commits)
  tracing: Have stack tracer trace full stack
  tracing: Export trace_dump_stack to modules
  tracing: probeevent: Fix uninitialized used of offset in parse args
  tracing/kprobes: Allow kprobe-events to record module symbol
  tracing/kprobes: Check the probe on unloaded module correctly
  tracing/uprobes: Fix to return -EFAULT if copy_from_user failed
  tracing: probeevent: Add $argN for accessing function args
  x86: ptrace: Add function argument access API
  tracing: probeevent: Add array type support
  tracing: probeevent: Add symbol type
  tracing: probeevent: Unify fetch_insn processing common part
  tracing: probeevent: Append traceprobe_ for exported function
  tracing: probeevent: Return consumed bytes of dynamic area
  tracing: probeevent: Unify fetch type tables
  tracing: probeevent: Introduce new argument fetching code
  tracing: probeevent: Remove NOKPROBE_SYMBOL from print functions
  tracing: probeevent: Cleanup argument field definition
  tracing: probeevent: Cleanup print argument functions
  trace_uprobe: support reference counter in fd-based uprobe
  perf probe: Support SDT markers having reference counter (semaphore)
  ...

Documentation/trace/kprobetrace.rst

@@ -45,16 +45,18 @@ Synopsis of kprobe_events
   @SYM[+|-offs]	: Fetch memory at SYM +|- offs (SYM should be a data symbol)
   $stackN	: Fetch Nth entry of stack (N >= 0)
   $stack	: Fetch stack address.
-  $retval	: Fetch return value.(*)
+  $argN		: Fetch the Nth function argument. (N >= 1) (\*1)
+  $retval	: Fetch return value.(\*2)
   $comm		: Fetch current task comm.
-  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(\*3)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
 		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
 		  (x8/x16/x32/x64), "string" and bitfield are supported.
 
-  (*) only for return probe.
-  (**) this is useful for fetching a field of data structures.
+  (\*1) only for the probe on function entry (offs == 0).
+  (\*2) only for return probe.
+  (\*3) this is useful for fetching a field of data structures.
 
 Types
 -----
@@ -64,14 +66,27 @@ respectively. 'x' prefix implies it is unsigned. Traced arguments are shown
 in decimal ('s' and 'u') or hexadecimal ('x'). Without type casting, 'x32'
 or 'x64' is used depends on the architecture (e.g. x86-32 uses x32, and
 x86-64 uses x64).
+These value types can be an array. To record array data, you can add '[N]'
+(where N is a fixed number, less than 64) to the base type.
+E.g. 'x16[4]' means an array of x16 (2bytes hex) with 4 elements.
+Note that the array can be applied to memory type fetchargs, you can not
+apply it to registers/stack-entries etc. (for example, '$stack1:x8[8]' is
+wrong, but '+8($stack):x8[8]' is OK.)
 String type is a special type, which fetches a "null-terminated" string from
 kernel space. This means it will fail and store NULL if the string container
 has been paged out.
+The string array type is a bit different from other types. For other base
+types, <base-type>[1] is equal to <base-type> (e.g. +0(%di):x32[1] is same
+as +0(%di):x32.) But string[1] is not equal to string. The string type itself
+represents "char array", but string array type represents "char * array".
+So, for example, +0(%di):string[1] is equal to +0(+0(%di)):string.
 Bitfield is another special type, which takes 3 parameters, bit-width, bit-
 offset, and container-size (usually 32). The syntax is::
 
  b<bit-width>@<bit-offset>/<container-size>
 
+Symbol type('symbol') is an alias of u32 or u64 type (depends on BITS_PER_LONG)
+which shows given pointer in "symbol+offset" style.
 For $comm, the default type is "string"; any other type is invalid.
 
 

arch/Kconfig

@@ -290,6 +290,13 @@ config HAVE_RSEQ
 	  This symbol should be selected by an architecture if it
 	  supports an implementation of restartable sequences.
 
+config HAVE_FUNCTION_ARG_ACCESS_API
+	bool
+	help
+	  This symbol should be selected by an architecure if it supports
+	  the API needed to access function arguments from pt_regs,
+	  declared in asm/ptrace.h
+
 config HAVE_CLK
 	bool
 	help

arch/x86/Kconfig

@@ -186,6 +186,7 @@ config X86
 	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_RSEQ

arch/x86/include/asm/ptrace.h

@@ -286,6 +286,44 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 	return 0;
 }
 
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ * Note that this chooses most probably assignment, in some case
+ * it can be incorrect.
+ * This is expected to be called from kprobes or ftrace with regs
+ * where the top of stack is the return address.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						     unsigned int n)
+{
+	static const unsigned int argument_offs[] = {
+#ifdef __i386__
+		offsetof(struct pt_regs, ax),
+		offsetof(struct pt_regs, cx),
+		offsetof(struct pt_regs, dx),
+#define NR_REG_ARGUMENTS 3
+#else
+		offsetof(struct pt_regs, di),
+		offsetof(struct pt_regs, si),
+		offsetof(struct pt_regs, dx),
+		offsetof(struct pt_regs, cx),
+		offsetof(struct pt_regs, r8),
+		offsetof(struct pt_regs, r9),
+#define NR_REG_ARGUMENTS 6
+#endif
+	};
+
+	if (n >= NR_REG_ARGUMENTS) {
+		n -= NR_REG_ARGUMENTS - 1;
+		return regs_get_kernel_stack_nth(regs, n);
+	} else
+		return regs_get_register(regs, argument_offs[n]);
+}
+
 #define arch_has_single_step()	(1)
 #ifdef CONFIG_X86_DEBUGCTLMSR
 #define arch_has_block_step()	(1)

include/linux/trace_events.h

@@ -575,7 +575,8 @@ extern int bpf_get_kprobe_info(const struct perf_event *event,
 			       bool perf_type_tracepoint);
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
-extern int  perf_uprobe_init(struct perf_event *event, bool is_retprobe);
+extern int  perf_uprobe_init(struct perf_event *event,
+			     unsigned long ref_ctr_offset, bool is_retprobe);
 extern void perf_uprobe_destroy(struct perf_event *event);
 extern int bpf_get_uprobe_info(const struct perf_event *event,
 			       u32 *fd_type, const char **filename,

include/linux/uprobes.h

@@ -123,6 +123,7 @@ extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
+extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_mmap(struct vm_area_struct *vma);
@@ -160,6 +161,10 @@ uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
 {
 	return -ENOSYS;
 }
+static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc)
+{
+	return -ENOSYS;
+}
 static inline int
 uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add)
 {

kernel/events/core.c

@@ -8376,30 +8376,39 @@ static struct pmu perf_tracepoint = {
  *
  * PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe
  *                               if not set, create kprobe/uprobe
+ *
+ * The following values specify a reference counter (or semaphore in the
+ * terminology of tools like dtrace, systemtap, etc.) Userspace Statically
+ * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset.
+ *
+ * PERF_UPROBE_REF_CTR_OFFSET_BITS	# of bits in config as th offset
+ * PERF_UPROBE_REF_CTR_OFFSET_SHIFT	# of bits to shift left
  */
 enum perf_probe_config {
 	PERF_PROBE_CONFIG_IS_RETPROBE = 1U << 0,  /* [k,u]retprobe */
+	PERF_UPROBE_REF_CTR_OFFSET_BITS = 32,
+	PERF_UPROBE_REF_CTR_OFFSET_SHIFT = 64 - PERF_UPROBE_REF_CTR_OFFSET_BITS,
 };
 
 PMU_FORMAT_ATTR(retprobe, "config:0");
+#endif
 
-static struct attribute *probe_attrs[] = {
+#ifdef CONFIG_KPROBE_EVENTS
+static struct attribute *kprobe_attrs[] = {
 	&format_attr_retprobe.attr,
 	NULL,
 };
 
-static struct attribute_group probe_format_group = {
+static struct attribute_group kprobe_format_group = {
 	.name = "format",
-	.attrs = probe_attrs,
+	.attrs = kprobe_attrs,
 };
 
-static const struct attribute_group *probe_attr_groups[] = {
-	&probe_format_group,
+static const struct attribute_group *kprobe_attr_groups[] = {
+	&kprobe_format_group,
 	NULL,
 };
-#endif
 
-#ifdef CONFIG_KPROBE_EVENTS
 static int perf_kprobe_event_init(struct perf_event *event);
 static struct pmu perf_kprobe = {
 	.task_ctx_nr	= perf_sw_context,
@@ -8409,7 +8418,7 @@ static struct pmu perf_kprobe = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-	.attr_groups	= probe_attr_groups,
+	.attr_groups	= kprobe_attr_groups,
 };
 
 static int perf_kprobe_event_init(struct perf_event *event)
@@ -8441,6 +8450,24 @@ static int perf_kprobe_event_init(struct perf_event *event)
 #endif /* CONFIG_KPROBE_EVENTS */
 
 #ifdef CONFIG_UPROBE_EVENTS
+PMU_FORMAT_ATTR(ref_ctr_offset, "config:32-63");
+
+static struct attribute *uprobe_attrs[] = {
+	&format_attr_retprobe.attr,
+	&format_attr_ref_ctr_offset.attr,
+	NULL,
+};
+
+static struct attribute_group uprobe_format_group = {
+	.name = "format",
+	.attrs = uprobe_attrs,
+};
+
+static const struct attribute_group *uprobe_attr_groups[] = {
+	&uprobe_format_group,
+	NULL,
+};
+
 static int perf_uprobe_event_init(struct perf_event *event);
 static struct pmu perf_uprobe = {
 	.task_ctx_nr	= perf_sw_context,
@@ -8450,12 +8477,13 @@ static struct pmu perf_uprobe = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-	.attr_groups	= probe_attr_groups,
+	.attr_groups	= uprobe_attr_groups,
 };
 
 static int perf_uprobe_event_init(struct perf_event *event)
 {
 	int err;
+	unsigned long ref_ctr_offset;
 	bool is_retprobe;
 
 	if (event->attr.type != perf_uprobe.type)
@@ -8471,7 +8499,8 @@ static int perf_uprobe_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 
 	is_retprobe = event->attr.config & PERF_PROBE_CONFIG_IS_RETPROBE;
-	err = perf_uprobe_init(event, is_retprobe);
+	ref_ctr_offset = event->attr.config >> PERF_UPROBE_REF_CTR_OFFSET_SHIFT;
+	err = perf_uprobe_init(event, ref_ctr_offset, is_retprobe);
 	if (err)
 		return err;