Merge tag 'trace-v6.1' of git://git.kernel.org/pub/scm/linux/kernel/g…

…it/trace/linux-trace

Pull tracing updates from Steven Rostedt:
 "Major changes:

   - Changed location of tracing repo from personal git repo to:
     git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git

   - Added Masami Hiramatsu as co-maintainer

   - Updated MAINTAINERS file to separate out FTRACE as it is more than
     just TRACING.

  Minor changes:

   - Added Mark Rutland as FTRACE reviewer

   - Updated user_events to make it on its way to remove the BROKEN tag.
     The changes should now be acceptable but will run it through a
     cycle and hopefully we can remove the BROKEN tag next release.

   - Added filtering to eprobes

   - Added a delta time to the benchmark trace event

   - Have the histogram and filter callbacks called via a switch
     statement instead of indirect functions. This speeds it up to avoid
     retpolines.

   - Add a way to wake up ring buffer waiters waiting for the ring
     buffer to fill up to its watermark.

   - New ioctl() on the trace_pipe_raw file to wake up ring buffer
     waiters.

   - Wake up waiters when the ring buffer is disabled. A reader may
     block when the ring buffer is disabled, but if it was blocked when
     the ring buffer is disabled it should then wake up.

  Fixes:

   - Allow splice to read partially read ring buffer pages. This fixes
     splice never moving forward.

   - Fix inverted compare that made the "shortest" ring buffer wait
     queue actually the longest.

   - Fix a race in the ring buffer between resetting a page when a
     writer goes to another page, and the reader.

   - Fix ftrace accounting bug when function hooks are added at boot up
     before the weak functions are set to "disabled".

   - Fix bug that freed a user allocated snapshot buffer when enabling a
     tracer.

   - Fix possible recursive locks in osnoise tracer

   - Fix recursive locking direct functions

   - Other minor clean ups and fixes"

* tag 'trace-v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (44 commits)
  ftrace: Create separate entry in MAINTAINERS for function hooks
  tracing: Update MAINTAINERS to reflect new tracing git repo
  tracing: Do not free snapshot if tracer is on cmdline
  ftrace: Still disable enabled records marked as disabled
  tracing/user_events: Move pages/locks into groups to prepare for namespaces
  tracing: Add Masami Hiramatsu as co-maintainer
  tracing: Remove unused variable 'dups'
  MAINTAINERS: add myself as a tracing reviewer
  ring-buffer: Fix race between reset page and reading page
  tracing/user_events: Update ABI documentation to align to bits vs bytes
  tracing/user_events: Use bits vs bytes for enabled status page data
  tracing/user_events: Use refcount instead of atomic for ref tracking
  tracing/user_events: Ensure user provided strings are safely formatted
  tracing/user_events: Use WRITE instead of READ for io vector import
  tracing/user_events: Use NULL for strstr checks
  tracing: Fix spelling mistake "preapre" -> "prepare"
  tracing: Wake up waiters when tracing is disabled
  tracing: Add ioctl() to force ring buffer waiters to wake up
  tracing: Wake up ring buffer waiters on closing of the file
  ring-buffer: Add ring_buffer_wake_waiters()
  ...

Documentation/trace/user_events.rst

@@ -20,14 +20,14 @@ dynamic_events is the same as the ioctl with the u: prefix applied.
 
 Typically programs will register a set of events that they wish to expose to
 tools that can read trace_events (such as ftrace and perf). The registration
-process gives back two ints to the program for each event. The first int is the
-status index. This index describes which byte in the
+process gives back two ints to the program for each event. The first int is
+the status bit. This describes which bit in little-endian format in the
 /sys/kernel/debug/tracing/user_events_status file represents this event. The
-second int is the write index. This index describes the data when a write() or
+second int is the write index which describes the data when a write() or
 writev() is called on the /sys/kernel/debug/tracing/user_events_data file.
 
-The structures referenced in this document are contained with the
-/include/uap/linux/user_events.h file in the source tree.
+The structures referenced in this document are contained within the
+/include/uapi/linux/user_events.h file in the source tree.
 
 **NOTE:** *Both user_events_status and user_events_data are under the tracefs
 filesystem and may be mounted at different paths than above.*
@@ -38,18 +38,18 @@ Registering within a user process is done via ioctl() out to the
 /sys/kernel/debug/tracing/user_events_data file. The command to issue is
 DIAG_IOCSREG.
 
-This command takes a struct user_reg as an argument::
+This command takes a packed struct user_reg as an argument::
 
   struct user_reg {
         u32 size;
         u64 name_args;
-        u32 status_index;
+        u32 status_bit;
         u32 write_index;
   };
 
 The struct user_reg requires two inputs, the first is the size of the structure
 to ensure forward and backward compatibility. The second is the command string
-to issue for registering. Upon success two outputs are set, the status index
+to issue for registering. Upon success two outputs are set, the status bit
 and the write index.
 
 User based events show up under tracefs like any other event under the
@@ -111,15 +111,56 @@ in realtime. This allows user programs to only incur the cost of the write() or
 writev() calls when something is actively attached to the event.
 
 User programs call mmap() on /sys/kernel/debug/tracing/user_events_status to
-check the status for each event that is registered. The byte to check in the
-file is given back after the register ioctl() via user_reg.status_index.
+check the status for each event that is registered. The bit to check in the
+file is given back after the register ioctl() via user_reg.status_bit. The bit
+is always in little-endian format. Programs can check if the bit is set either
+using a byte-wise index with a mask or a long-wise index with a little-endian
+mask.
+
 Currently the size of user_events_status is a single page, however, custom
 kernel configurations can change this size to allow more user based events. In
 all cases the size of the file is a multiple of a page size.
 
-For example, if the register ioctl() gives back a status_index of 3 you would
-check byte 3 of the returned mmap data to see if anything is attached to that
-event.
+For example, if the register ioctl() gives back a status_bit of 3 you would
+check byte 0 (3 / 8) of the returned mmap data and then AND the result with 8
+(1 << (3 % 8)) to see if anything is attached to that event.
+
+A byte-wise index check is performed as follows::
+
+  int index, mask;
+  char *status_page;
+
+  index = status_bit / 8;
+  mask = 1 << (status_bit % 8);
+
+  ...
+
+  if (status_page[index] & mask) {
+        /* Enabled */
+  }
+
+A long-wise index check is performed as follows::
+
+  #include <asm/bitsperlong.h>
+  #include <endian.h>
+
+  #if __BITS_PER_LONG == 64
+  #define endian_swap(x) htole64(x)
+  #else
+  #define endian_swap(x) htole32(x)
+  #endif
+
+  long index, mask, *status_page;
+
+  index = status_bit / __BITS_PER_LONG;
+  mask = 1L << (status_bit % __BITS_PER_LONG);
+  mask = endian_swap(mask);
+
+  ...
+
+  if (status_page[index] & mask) {
+        /* Enabled */
+  }
 
 Administrators can easily check the status of all registered events by reading
 the user_events_status file directly via a terminal. The output is as follows::
@@ -137,29 +178,18 @@ For example, on a system that has a single event the output looks like this::
 
   Active: 1
   Busy: 0
-  Max: 4096
+  Max: 32768
 
 If a user enables the user event via ftrace, the output would change to this::
 
   1:test # Used by ftrace
 
   Active: 1
   Busy: 1
-  Max: 4096
-
-**NOTE:** *A status index of 0 will never be returned. This allows user
-programs to have an index that can be used on error cases.*
-
-Status Bits
-^^^^^^^^^^^
-The byte being checked will be non-zero if anything is attached. Programs can
-check specific bits in the byte to see what mechanism has been attached.
-
-The following values are defined to aid in checking what has been attached:
-
-**EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0).
+  Max: 32768
 
-**EVENT_STATUS_PERF** - Bit set if perf has been attached (Bit 1).
+**NOTE:** *A status bit of 0 will never be returned. This allows user programs
+to have a bit that can be used on error cases.*
 
 Writing Data
 ------------

MAINTAINERS

@@ -8433,6 +8433,19 @@ L:	[email protected]
 S:	Maintained
 F:	drivers/platform/x86/fujitsu-tablet.c
 
+FUNCTION HOOKS (FTRACE)
+M:	Steven Rostedt <[email protected]>
+M:	Masami Hiramatsu <[email protected]>
+R:	Mark Rutland <[email protected]>
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
+F:	Documentation/trace/ftrace*
+F:	kernel/trace/ftrace*
+F:	kernel/trace/fgraph.c
+F:	arch/*/*/*/*ftrace*
+F:	arch/*/*/*ftrace*
+F:	include/*/ftrace.h
+
 FUNGIBLE ETHERNET DRIVERS
 M:	Dimitris Michailidis <[email protected]>
 L:	[email protected]
@@ -11422,7 +11435,7 @@ M:	Anil S Keshavamurthy <[email protected]>
 M:	"David S. Miller" <[email protected]>
 M:	Masami Hiramatsu <[email protected]>
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/kprobes.rst
 F:	include/asm-generic/kprobes.h
 F:	include/linux/kprobes.h
@@ -20771,14 +20784,11 @@ F:	drivers/hwmon/pmbus/tps546d24.c
 
 TRACING
 M:	Steven Rostedt <[email protected]>
-M:	Ingo Molnar <[email protected]>
+M:	Masami Hiramatsu <[email protected]>
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
-F:	Documentation/trace/ftrace.rst
-F:	arch/*/*/*/*ftrace*
-F:	arch/*/*/*ftrace*
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
+F:	Documentation/trace/*
 F:	fs/tracefs/
-F:	include/*/ftrace.h
 F:	include/linux/trace*.h
 F:	include/trace/
 F:	kernel/trace/
@@ -20787,7 +20797,7 @@ F:	tools/testing/selftests/ftrace/
 
 TRACING MMIO ACCESSES (MMIOTRACE)
 M:	Steven Rostedt <[email protected]>
-M:	Ingo Molnar <mingo@kernel.org>
+M:	Masami Hiramatsu <mhiramat@kernel.org>
 R:	Karol Herbst <[email protected]>
 R:	Pekka Paalanen <[email protected]>
 L:	[email protected]

arch/x86/include/asm/ftrace.h

@@ -23,7 +23,6 @@
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
 #ifndef __ASSEMBLY__
-extern atomic_t modifying_ftrace_code;
 extern void __fentry__(void);
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)

arch/x86/include/asm/kprobes.h

@@ -50,8 +50,6 @@ extern const int kretprobe_blacklist_size;
 
 void arch_remove_kprobe(struct kprobe *p);
 
-extern void arch_kprobe_override_function(struct pt_regs *regs);
-
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */

arch/x86/kernel/kprobes/core.c

@@ -59,8 +59,6 @@
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
-#define stack_addr(regs) ((unsigned long *)regs->sp)
-
 #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
 	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
 	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \

include/linux/ftrace.h

@@ -1122,47 +1122,6 @@ static inline void unpause_graph_tracing(void) { }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 #ifdef CONFIG_TRACING
-
-/* flags for current->trace */
-enum {
-	TSK_TRACE_FL_TRACE_BIT	= 0,
-	TSK_TRACE_FL_GRAPH_BIT	= 1,
-};
-enum {
-	TSK_TRACE_FL_TRACE	= 1 << TSK_TRACE_FL_TRACE_BIT,
-	TSK_TRACE_FL_GRAPH	= 1 << TSK_TRACE_FL_GRAPH_BIT,
-};
-
-static inline void set_tsk_trace_trace(struct task_struct *tsk)
-{
-	set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
-}
-
-static inline void clear_tsk_trace_trace(struct task_struct *tsk)
-{
-	clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
-}
-
-static inline int test_tsk_trace_trace(struct task_struct *tsk)
-{
-	return tsk->trace & TSK_TRACE_FL_TRACE;
-}
-
-static inline void set_tsk_trace_graph(struct task_struct *tsk)
-{
-	set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
-}
-
-static inline void clear_tsk_trace_graph(struct task_struct *tsk)
-{
-	clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
-}
-
-static inline int test_tsk_trace_graph(struct task_struct *tsk)
-{
-	return tsk->trace & TSK_TRACE_FL_GRAPH;
-}
-
 enum ftrace_dump_mode;
 
 extern enum ftrace_dump_mode ftrace_dump_on_oops;

include/linux/ring_buffer.h

@@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full);
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
-
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu);
 
 #define RING_BUFFER_ALL_CPUS -1
 

include/linux/sched.h

@@ -1390,9 +1390,6 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_TRACING
-	/* State flags for use by tracers: */
-	unsigned long			trace;
-
 	/* Bitmask and counter of trace recursion: */
 	unsigned long			trace_recursion;
 #endif /* CONFIG_TRACING */

include/linux/trace_events.h

@@ -92,6 +92,7 @@ struct trace_iterator {
 	unsigned int		temp_size;
 	char			*fmt;	/* modified format holder */
 	unsigned int		fmt_size;
+	long			wait_index;
 
 	/* trace_seq for __print_flags() and __print_symbolic() etc. */
 	struct trace_seq	tmp_seq;

include/linux/user_events.h

@@ -20,15 +20,6 @@
 #define USER_EVENTS_SYSTEM "user_events"
 #define USER_EVENTS_PREFIX "u:"
 
-/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */
-#define EVENT_BIT_FTRACE 0
-#define EVENT_BIT_PERF 1
-#define EVENT_BIT_OTHER 7
-
-#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE)
-#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF)
-#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER)
-
 /* Create dynamic location entry within a 32-bit value */
 #define DYN_LOC(offset, size) ((size) << 16 | (offset))
 
@@ -45,12 +36,12 @@ struct user_reg {
 	/* Input: Pointer to string with event name, description and flags */
 	__u64 name_args;
 
-	/* Output: Byte index of the event within the status page */
-	__u32 status_index;
+	/* Output: Bitwise index of the event within the status page */
+	__u32 status_bit;
 
 	/* Output: Index of the event to use when writing data */
 	__u32 write_index;
-};
+} __attribute__((__packed__));
 
 #define DIAG_IOC_MAGIC '*'