Merge tag 'trace-v6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:
 "Main user visible change:

   - User events can now have "multi formats"

     The current user events have a single format. If another event is
     created with a different format, it will fail to be created. That
     is, once an event name is used, it cannot be used again with a
     different format. This can cause issues if a library is using an
     event and updates its format. An application using the older format
     will prevent an application using the new library from registering
     its event.

     A task could also DOS another application if it knows the event
     names, and it creates events with different formats.

     The multi-format event is in a different name space from the single
     format. Both the event name and its format are the unique
     identifier. This will allow two different applications to use the
     same user event name but with different payloads.

   - Added support to have ftrace_dump_on_oops dump out instances and
     not just the main top level tracing buffer.

  Other changes:

   - Add eventfs_root_inode

     Only the root inode has a dentry that is static (never goes away)
     and stores it upon creation. There's no reason that the thousands
     of other eventfs inodes should have a pointer that never gets set
     in its descriptor. Create a eventfs_root_inode desciptor that has a
     eventfs_inode descriptor and a dentry pointer, and only the root
     inode will use this.

   - Added WARN_ON()s in eventfs

     There's some conditionals remaining in eventfs that should never be
     hit, but instead of removing them, add WARN_ON() around them to
     make sure that they are never hit.

   - Have saved_cmdlines allocation also include the map_cmdline_to_pid
     array

     The saved_cmdlines structure allocates a large amount of data to
     hold its mappings. Within it, it has three arrays. Two are already
     apart of it: map_pid_to_cmdline[] and saved_cmdlines[]. More memory
     can be saved by also including the map_cmdline_to_pid[] array as
     well.

   - Restructure __string() and __assign_str() macros used in
     TRACE_EVENT()

     Dynamic strings in TRACE_EVENT() are declared with:

         __string(name, source)

     And assigned with:

        __assign_str(name, source)

     In the tracepoint callback of the event, the __string() is used to
     get the size needed to allocate on the ring buffer and
     __assign_str() is used to copy the string into the ring buffer.
     There's a helper structure that is created in the TRACE_EVENT()
     macro logic that will hold the string length and its position in
     the ring buffer which is created by __string().

     There are several trace events that have a function to create the
     string to save. This function is executed twice. Once for
     __string() and again for __assign_str(). There's no reason for
     this. The helper structure could also save the string it used in
     __string() and simply copy that into __assign_str() (it also
     already has its length).

     By using the structure to store the source string for the
     assignment, it means that the second argument to __assign_str() is
     no longer needed.

     It will be removed in the next merge window, but for now add a
     warning if the source string given to __string() is different than
     the source string given to __assign_str(), as the source to
     __assign_str() isn't even used and will be going away.

   - Added checks to make sure that the source of __string() is also the
     source of __assign_str() so that it can be safely removed in the
     next merge window.

     Included fixes that the above check found.

   - Other minor clean ups and fixes"

* tag 'trace-v6.9-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (34 commits)
  tracing: Add __string_src() helper to help compilers not to get confused
  tracing: Use strcmp() in __assign_str() WARN_ON() check
  tracepoints: Use WARN() and not WARN_ON() for warnings
  tracing: Use div64_u64() instead of do_div()
  tracing: Support to dump instance traces by ftrace_dump_on_oops
  tracing: Remove second parameter to __assign_rel_str()
  tracing: Add warning if string in __assign_str() does not match __string()
  tracing: Add __string_len() example
  tracing: Remove __assign_str_len()
  ftrace: Fix most kernel-doc warnings
  tracing: Decrement the snapshot if the snapshot trigger fails to register
  tracing: Fix snapshot counter going between two tracers that use it
  tracing: Use EVENT_NULL_STR macro instead of open coding "(null)"
  tracing: Use ? : shortcut in trace macros
  tracing: Do not calculate strlen() twice for __string() fields
  tracing: Rework __assign_str() and __string() to not duplicate getting the string
  cxl/trace: Properly initialize cxl_poison region name
  net: hns3: tracing: fix hclgevf trace event strings
  drm/i915: Add missing ; to __assign_str() macros in tracepoint code
  NFSD: Fix nfsd_clid_class use of __string_len() macro
  ...

10 files changed, 1007 insertions, 712 deletions

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 157f7ce2942d..81cc974913bb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1710,9 +1710,9 @@ static struct ctl_table kern_table[] = {
 	{
 		.procname	= "ftrace_dump_on_oops",
 		.data		= &ftrace_dump_on_oops,
-		.maxlen		= sizeof(int),
+		.maxlen		= MAX_TRACER_SIZE,
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dostring,
 	},
 	{
 		.procname	= "traceoff_on_warning",
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 83ba342aef31..da1710499698 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1160,7 +1160,7 @@ __ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
  * Search a given @hash to see if a given instruction pointer (@ip)
  * exists in it.
  *
- * Returns the entry that holds the @ip if found. NULL otherwise.
+ * Returns: the entry that holds the @ip if found. NULL otherwise.
  */
 struct ftrace_func_entry *
 ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
@@ -1282,7 +1282,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 
 /**
  * ftrace_free_filter - remove all filters for an ftrace_ops
- * @ops - the ops to remove the filters from
+ * @ops: the ops to remove the filters from
  */
 void ftrace_free_filter(struct ftrace_ops *ops)
 {
@@ -1587,7 +1587,7 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end)
  * @end: end of range to search (inclusive). @end points to the last byte
  *	to check.
  *
- * Returns rec->ip if the related ftrace location is a least partly within
+ * Returns: rec->ip if the related ftrace location is a least partly within
  * the given address range. That is, the first address of the instruction
  * that is either a NOP or call to the function tracer. It checks the ftrace
  * internal tables to determine if the address belongs or not.
@@ -1607,9 +1607,10 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end)
  * ftrace_location - return the ftrace location
  * @ip: the instruction pointer to check
  *
- * If @ip matches the ftrace location, return @ip.
- * If @ip matches sym+0, return sym's ftrace location.
- * Otherwise, return 0.
+ * Returns:
+ * * If @ip matches the ftrace location, return @ip.
+ * * If @ip matches sym+0, return sym's ftrace location.
+ * * Otherwise, return 0.
  */
 unsigned long ftrace_location(unsigned long ip)
 {
@@ -1639,7 +1640,7 @@ out:
  * @start: start of range to search
  * @end: end of range to search (inclusive). @end points to the last byte to check.
  *
- * Returns 1 if @start and @end contains a ftrace location.
+ * Returns: 1 if @start and @end contains a ftrace location.
  * That is, the instruction that is either a NOP or call to
  * the function tracer. It checks the ftrace internal tables to
  * determine if the address belongs or not.
@@ -2574,7 +2575,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
  * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
  * is not set, then it wants to convert to the normal callback.
  *
- * Returns the address of the trampoline to set to
+ * Returns: the address of the trampoline to set to
  */
 unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
 {
@@ -2615,7 +2616,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
  * a function that saves all the regs. Basically the '_EN' version
  * represents the current state of the function.
  *
- * Returns the address of the trampoline that is currently being called
+ * Returns: the address of the trampoline that is currently being called
  */
 unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
 {
@@ -2719,7 +2720,7 @@ struct ftrace_rec_iter {
 /**
  * ftrace_rec_iter_start - start up iterating over traced functions
  *
- * Returns an iterator handle that is used to iterate over all
+ * Returns: an iterator handle that is used to iterate over all
  * the records that represent address locations where functions
  * are traced.
  *
@@ -2751,7 +2752,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void)
  * ftrace_rec_iter_next - get the next record to process.
  * @iter: The handle to the iterator.
  *
- * Returns the next iterator after the given iterator @iter.
+ * Returns: the next iterator after the given iterator @iter.
  */
 struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter)
 {
@@ -2776,7 +2777,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter)
  * ftrace_rec_iter_record - get the record at the iterator location
  * @iter: The current iterator location
  *
- * Returns the record that the current @iter is at.
+ * Returns: the record that the current @iter is at.
  */
 struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter)
 {
@@ -4010,6 +4011,8 @@ ftrace_avail_addrs_open(struct inode *inode, struct file *file)
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
  * tracing_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
+ *
+ * Returns: 0 on success or a negative errno value on failure
  */
 int
 ftrace_regex_open(struct ftrace_ops *ops, int flag,
@@ -4626,7 +4629,7 @@ struct ftrace_func_mapper {
 /**
  * allocate_ftrace_func_mapper - allocate a new ftrace_func_mapper
  *
- * Returns a ftrace_func_mapper descriptor that can be used to map ips to data.
+ * Returns: a ftrace_func_mapper descriptor that can be used to map ips to data.
  */
 struct ftrace_func_mapper *allocate_ftrace_func_mapper(void)
 {
@@ -4646,7 +4649,7 @@ struct ftrace_func_mapper *allocate_ftrace_func_mapper(void)
  * @mapper: The mapper that has the ip maps
  * @ip: the instruction pointer to find the data for
  *
- * Returns the data mapped to @ip if found otherwise NULL. The return
+ * Returns: the data mapped to @ip if found otherwise NULL. The return
  * is actually the address of the mapper data pointer. The address is
  * returned for use cases where the data is no bigger than a long, and
  * the user can use the data pointer as its data instead of having to
@@ -4672,7 +4675,7 @@ void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
  * @ip: The instruction pointer address to map @data to
  * @data: The data to map to @ip
  *
- * Returns 0 on success otherwise an error.
+ * Returns: 0 on success otherwise an error.
  */
 int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
 			      unsigned long ip, void *data)
@@ -4701,7 +4704,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
  * @mapper: The mapper that has the ip maps
  * @ip: The instruction pointer address to remove the data from
  *
- * Returns the data if it is found, otherwise NULL.
+ * Returns: the data if it is found, otherwise NULL.
  * Note, if the data pointer is used as the data itself, (see
  * ftrace_func_mapper_find_ip(), then the return value may be meaningless,
  * if the data pointer was set to zero.
@@ -5625,10 +5628,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct);
 
 /**
  * ftrace_set_filter_ip - set a function to filter on in ftrace by address
- * @ops - the ops to set the filter with
- * @ip - the address to add to or remove from the filter.
- * @remove - non zero to remove the ip from the filter
- * @reset - non zero to reset all filters before applying this filter.
+ * @ops: the ops to set the filter with
+ * @ip: the address to add to or remove from the filter.
+ * @remove: non zero to remove the ip from the filter
+ * @reset: non zero to reset all filters before applying this filter.
  *
  * Filters denote which functions should be enabled when tracing is enabled
  * If @ip is NULL, it fails to update filter.
@@ -5647,11 +5650,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
 
 /**
  * ftrace_set_filter_ips - set functions to filter on in ftrace by addresses
- * @ops - the ops to set the filter with
- * @ips - the array of addresses to add to or remove from the filter.
- * @cnt - the number of addresses in @ips
- * @remove - non zero to remove ips from the filter
- * @reset - non zero to reset all filters before applying this filter.
+ * @ops: the ops to set the filter with
+ * @ips: the array of addresses to add to or remove from the filter.
+ * @cnt: the number of addresses in @ips
+ * @remove: non zero to remove ips from the filter
+ * @reset: non zero to reset all filters before applying this filter.
  *
  * Filters denote which functions should be enabled when tracing is enabled
  * If @ips array or any ip specified within is NULL , it fails to update filter.
@@ -5670,7 +5673,7 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ips);
 
 /**
  * ftrace_ops_set_global_filter - setup ops to use global filters
- * @ops - the ops which will use the global filters
+ * @ops: the ops which will use the global filters
  *
  * ftrace users who need global function trace filtering should call this.
  * It can set the global filter only if ops were not initialized before.
@@ -5694,10 +5697,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 
 /**
  * ftrace_set_filter - set a function to filter on in ftrace
- * @ops - the ops to set the filter with
- * @buf - the string that holds the function filter text.
- * @len - the length of the string.
- * @reset - non zero to reset all filters before applying this filter.
+ * @ops: the ops to set the filter with
+ * @buf: the string that holds the function filter text.
+ * @len: the length of the string.
+ * @reset: non-zero to reset all filters before applying this filter.
  *
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
@@ -5716,10 +5719,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
 
 /**
  * ftrace_set_notrace - set a function to not trace in ftrace
- * @ops - the ops to set the notrace filter with
- * @buf - the string that holds the function notrace text.
- * @len - the length of the string.
- * @reset - non zero to reset all filters before applying this filter.
+ * @ops: the ops to set the notrace filter with
+ * @buf: the string that holds the function notrace text.
+ * @len: the length of the string.
+ * @reset: non-zero to reset all filters before applying this filter.
  *
  * Notrace Filters denote which functions should not be enabled when tracing
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
@@ -5738,9 +5741,9 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 EXPORT_SYMBOL_GPL(ftrace_set_notrace);
 /**
  * ftrace_set_global_filter - set a function to filter on with global tracers
- * @buf - the string that holds the function filter text.
- * @len - the length of the string.
- * @reset - non zero to reset all filters before applying this filter.
+ * @buf: the string that holds the function filter text.
+ * @len: the length of the string.
+ * @reset: non-zero to reset all filters before applying this filter.
  *
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
@@ -5753,9 +5756,9 @@ EXPORT_SYMBOL_GPL(ftrace_set_global_filter);
 
 /**
  * ftrace_set_global_notrace - set a function to not trace with global tracers
- * @buf - the string that holds the function notrace text.
- * @len - the length of the string.
- * @reset - non zero to reset all filters before applying this filter.
+ * @buf: the string that holds the function notrace text.
+ * @len: the length of the string.
+ * @reset: non-zero to reset all filters before applying this filter.
  *
  * Notrace Filters denote which functions should not be enabled when tracing
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
@@ -7443,7 +7446,7 @@ NOKPROBE_SYMBOL(ftrace_ops_assist_func);
  * have its own recursion protection, then it should call the
  * ftrace_ops_assist_func() instead.
  *
- * Returns the function that the trampoline should call for @ops.
+ * Returns: the function that the trampoline should call for @ops.
  */
 ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 {
@@ -7897,7 +7900,7 @@ void ftrace_kill(void)
 /**
  * ftrace_is_dead - Test if ftrace is dead or not.
  *
- * Returns 1 if ftrace is "dead", zero otherwise.
+ * Returns: 1 if ftrace is "dead", zero otherwise.
  */
 int ftrace_is_dead(void)
 {
@@ -8142,8 +8145,7 @@ static int kallsyms_callback(void *data, const char *name, unsigned long addr)
  * @addrs array, which needs to be big enough to store at least @cnt
  * addresses.
  *
- * This function returns 0 if all provided symbols are found,
- * -ESRCH otherwise.
+ * Returns: 0 if all provided symbols are found, -ESRCH otherwise.
  */
 int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
 {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 09df645ab9c7..25476ead681b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -384,6 +384,7 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
+	atomic_t			seq;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -753,6 +754,9 @@ static void rb_wake_up_waiters(struct irq_work *work)
 {
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
+	/* For waiters waiting for the first wake up */
+	(void)atomic_fetch_inc_release(&rbwork->seq);
+
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
 		/* Only cpu_buffer sets the above flags */
@@ -881,20 +885,21 @@ rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer,
 	return false;
 }
 
+struct rb_wait_data {
+	struct rb_irq_work		*irq_work;
+	int				seq;
+};
+
 /*
  * The default wait condition for ring_buffer_wait() is to just to exit the
  * wait loop the first time it is woken up.
  */
 static bool rb_wait_once(void *data)
 {
-	long *once = data;
-
-	/* wait_event() actually calls this twice before scheduling*/
-	if (*once > 1)
-		return true;
+	struct rb_wait_data *rdata = data;
+	struct rb_irq_work *rbwork = rdata->irq_work;
 
-	(*once)++;
-	return false;
+	return atomic_read_acquire(&rbwork->seq) != rdata->seq;
 }
 
 /**
@@ -915,14 +920,9 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full,
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct wait_queue_head *waitq;
 	struct rb_irq_work *rbwork;
-	long once = 0;
+	struct rb_wait_data rdata;
 	int ret = 0;
 
-	if (!cond) {
-		cond = rb_wait_once;
-		data = &once;
-	}
-
 	/*
 	 * Depending on what the caller is waiting for, either any
 	 * data in any cpu buffer, or a specific buffer, put the
@@ -944,6 +944,14 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full,
 	else
 		waitq = &rbwork->waiters;
 
+	/* Set up to exit loop as soon as it is woken */
+	if (!cond) {
+		cond = rb_wait_once;
+		rdata.irq_work = rbwork;
+		rdata.seq = atomic_read_acquire(&rbwork->seq);
+		data = &rdata;
+	}
+
 	ret = wait_event_interruptible((*waitq),
 				rb_wait_cond(rbwork, buffer, cpu, full, cond, data));
 
@@ -1515,7 +1523,8 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, pages);
 
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+					mflags | __GFP_ZERO,
 					cpu_buffer->buffer->subbuf_order);
 		if (!page)
 			goto free_pages;
@@ -1600,7 +1609,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 
 	cpu_buffer->reader_page = bpage;
 
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO,
+				cpu_buffer->buffer->subbuf_order);
 	if (!page)
 		goto fail_free_reader;
 	bpage->page = page_address(page);
@@ -4380,7 +4390,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 	cpu_buffer = iter->cpu_buffer;
 	reader = cpu_buffer->reader_page;
 	head_page = cpu_buffer->head_page;
-	commit_page = cpu_buffer->commit_page;
+	commit_page = READ_ONCE(cpu_buffer->commit_page);
 	commit_ts = commit_page->page->time_stamp;
 
 	/*
@@ -5568,7 +5578,8 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 	if (bpage->data)
 		goto out;
 
-	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
+	page = alloc_pages_node(cpu_to_node(cpu),
+				GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO,
 				cpu_buffer->buffer->subbuf_order);
 	if (!page) {
 		kfree(bpage);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ab4c1a1fbda8..233d1af39fff 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -13,7 +13,7 @@
  *  Copyright (C) 2004 Nadia Yvette Chambers
  */
 #include <linux/ring_buffer.h>
-#include <generated/utsrelease.h>
+#include <linux/utsname.h>
 #include <linux/stacktrace.h>
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
@@ -39,7 +39,6 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/panic_notifier.h>
-#include <linux/kmemleak.h>
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
@@ -105,7 +104,7 @@ dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
  * tracing is active, only save the comm when a trace event
  * occurred.
  */
-static DEFINE_PER_CPU(bool, trace_taskinfo_save);
+DEFINE_PER_CPU(bool, trace_taskinfo_save);
 
 /*
  * Kill all tracing for good (never come back).
@@ -131,9 +130,12 @@ cpumask_var_t __read_mostly	tracing_buffer_mask;
  * /proc/sys/kernel/ftrace_dump_on_oops
  * Set 1 if you want to dump buffers of all CPUs
  * Set 2 if you want to dump the buffer of the CPU that triggered oops
+ * Set instance name if you want to dump the specific trace instance
+ * Multiple instance dump is also supported, and instances are seperated
+ * by commas.
  */
-
-enum ftrace_dump_mode ftrace_dump_on_oops;
+/* Set to string format zero to disable by default */
+char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0";
 
 /* When set, tracing will stop when a WARN*() is hit */
 int __disable_trace_on_warning;
@@ -179,7 +181,6 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 				   struct trace_buffer *buffer,
 				   unsigned int trace_ctx);
 
-#define MAX_TRACER_SIZE		100
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
@@ -202,19 +203,33 @@ static int __init set_cmdline_ftrace(char *str)
 }
 __setup("ftrace=", set_cmdline_ftrace);
 
+int ftrace_dump_on_oops_enabled(void)
+{
+	if (!strcmp("0", ftrace_dump_on_oops))
+		return 0;
+	else
+		return 1;
+}
+
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-	if (*str++ != '=' || !*str || !strcmp("1", str)) {
-		ftrace_dump_on_oops = DUMP_ALL;
+	if (!*str) {
+		strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE);
 		return 1;
 	}
 
-	if (!strcmp("orig_cpu", str) || !strcmp("2", str)) {
-		ftrace_dump_on_oops = DUMP_ORIG;
-                return 1;
-        }
+	if (*str == ',') {
+		strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE);
+		strscpy(ftrace_dump_on_oops + 1, str, MAX_TRACER_SIZE - 1);
+		return 1;
+	}
+
+	if (*str++ == '=') {
+		strscpy(ftrace_dump_on_oops, str, MAX_TRACER_SIZE);
+		return 1;
+	}
 
-        return 0;
+	return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -1301,6 +1316,50 @@ static void free_snapshot(struct trace_array *tr)
 	tr->allocated_snapshot = false;
 }
 
+static int tracing_arm_snapshot_locked(struct trace_array *tr)
+{
+	int ret;
+
+	lockdep_assert_held(&trace_types_lock);
+
+	spin_lock(&tr->snapshot_trigger_lock);
+	if (tr->snapshot == UINT_MAX) {
+		spin_unlock(&tr->snapshot_trigger_lock);
+		return -EBUSY;
+	}
+
+	tr->snapshot++;
+	spin_unlock(&tr->snapshot_trigger_lock);
+
+	ret = tracing_alloc_snapshot_instance(tr);
+	if (ret) {
+		spin_lock(&tr->snapshot_trigger_lock);
+		tr->snapshot--;
+		spin_unlock(&tr->snapshot_trigger_lock);
+	}
+
+	return ret;
+}
+
+int tracing_arm_snapshot(struct trace_array *tr)
+{
+	int ret;
+
+	mutex_lock(&trace_types_lock);
+	ret = tracing_arm_snapshot_locked(tr);
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+}
+
+void tracing_disarm_snapshot(struct trace_array *tr)
+{
+	spin_lock(&tr->snapshot_trigger_lock);
+	if (!WARN_ON(!tr->snapshot))
+		tr->snapshot--;
+	spin_unlock(&tr->snapshot_trigger_lock);
+}
+
 /**
  * tracing_alloc_snapshot - allocate snapshot buffer.
  *
@@ -1374,10 +1433,6 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
 
 	mutex_lock(&trace_types_lock);
 
-	ret = tracing_alloc_snapshot_instance(tr);
-	if (ret)
-		goto fail_unlock;
-
 	if (tr->current_trace->use_max_tr) {
 		ret = -EBUSY;
 		goto fail_unlock;
@@ -1396,6 +1451,10 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
 		goto fail_unlock;
 	}
 
+	ret = tracing_arm_snapshot_locked(tr);
+	if (ret)
+		goto fail_unlock;
+
 	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	tr->cond_snapshot = cond_snapshot;
@@ -1440,6 +1499,8 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 	arch_spin_unlock(&tr->max_lock);
 	local_irq_enable();
 
+	tracing_disarm_snapshot(tr);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable);
@@ -1482,6 +1543,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 }
 EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable);
 #define free_snapshot(tr)	do { } while (0)
+#define tracing_arm_snapshot_locked(tr) ({ -EBUSY; })
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
 void tracer_tracing_off(struct trace_array *tr)
@@ -2320,98 +2382,6 @@ void tracing_reset_all_online_cpus(void)
 	mutex_unlock(&trace_types_lock);
 }
 
-/*
- * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
- * is the tgid last observed corresponding to pid=i.
- */
-static int *tgid_map;
-
-/* The maximum valid index into tgid_map. */
-static size_t tgid_map_max;
-
-#define SAVED_CMDLINES_DEFAULT 128
-#define NO_CMDLINE_MAP UINT_MAX
-/*
- * Preemption must be disabled before acquiring trace_cmdline_lock.
- * The various trace_arrays' max_lock must be acquired in a context
- * where interrupt is disabled.
- */
-static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-struct saved_cmdlines_buffer {
-	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
-	unsigned *map_cmdline_to_pid;
-	unsigned cmdline_num;
-	int cmdline_idx;
-	char saved_cmdlines[];
-};
-static struct saved_cmdlines_buffer *savedcmd;
-
-static inline char *get_saved_cmdlines(int idx)
-{
-	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
-}
-
-static inline void set_cmdline(int idx, const char *cmdline)
-{
-	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
-}
-
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
-	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
-
-	kfree(s->map_cmdline_to_pid);
-	kmemleak_free(s);
-	free_pages((unsigned long)s, order);
-}
-
-static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
-{
-	struct saved_cmdlines_buffer *s;
-	struct page *page;
-	int orig_size, size;
-	int order;
-
-	/* Figure out how much is needed to hold the given number of cmdlines */
-	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
-	order = get_order(orig_size);
-	size = 1 << (order + PAGE_SHIFT);
-	page = alloc_pages(GFP_KERNEL, order);
-	if (!page)
-		return NULL;
-
-	s = page_address(page);
-	kmemleak_alloc(s, size, 1, GFP_KERNEL);
-	memset(s, 0, sizeof(*s));
-
-	/* Round up to actual allocation */
-	val = (size - sizeof(*s)) / TASK_COMM_LEN;
-	s->cmdline_num = val;
-
-	s->map_cmdline_to_pid = kmalloc_array(val,
-					      sizeof(*s->map_cmdline_to_pid),
-					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid) {
-		free_saved_cmdlines_buffer(s);
-		return NULL;
-	}
-
-	s->cmdline_idx = 0;
-	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
-	       sizeof(s->map_pid_to_cmdline));
-	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
-	       val * sizeof(*s->map_cmdline_to_pid));
-
-	return s;
-}
-
-static int trace_create_savedcmd(void)
-{
-	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
-
-	return savedcmd ? 0 : -ENOMEM;
-}
-
 int is_tracing_stopped(void)
 {
 	return global_trace.stop_count;
@@ -2504,201 +2474,6 @@ void tracing_stop(void)
 	return tracing_stop_tr(&global_trace);
 }
 
-static int trace_save_cmdline(struct task_struct *tsk)
-{
-	unsigned tpid, idx;
-
-	/* treat recording of idle task as a success */
-	if (!tsk->pid)
-		return 1;
-
-	tpid = tsk->pid & (PID_MAX_DEFAULT - 1);
-
-	/*
-	 * It's not the end of the world if we don't get
-	 * the lock, but we also don't want to spin
-	 * nor do we want to disable interrupts,
-	 * so if we miss here, then better luck next time.
-	 *
-	 * This is called within the scheduler and wake up, so interrupts
-	 * had better been disabled and run queue lock been held.
-	 */
-	lockdep_assert_preemption_disabled();
-	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return 0;
-
-	idx = savedcmd->map_pid_to_cmdline[tpid];
-	if (idx == NO_CMDLINE_MAP) {
-		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
-
-		savedcmd->map_pid_to_cmdline[tpid] = idx;
-		savedcmd->cmdline_idx = idx;
-	}
-
-	savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
-	set_cmdline(idx, tsk->comm);
-
-	arch_spin_unlock(&trace_cmdline_lock);
-
-	return 1;
-}
-
-static void __trace_find_cmdline(int pid, char comm[])
-{
-	unsigned map;
-	int tpid;
-
-	if (!pid) {
-		strcpy(comm, "<idle>");
-		return;
-	}
-
-	if (WARN_ON_ONCE(pid < 0)) {
-		strcpy(comm, "<XXX>");
-		return;
-	}
-
-	tpid = pid & (PID_MAX_DEFAULT - 1);
-	map = savedcmd->map_pid_to_cmdline[tpid];
-	if (map != NO_CMDLINE_MAP) {
-		tpid = savedcmd->map_cmdline_to_pid[map];
-		if (tpid == pid) {
-			strscpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
-			return;
-		}
-	}
-	strcpy(comm, "<...>");
-}
-
-void trace_find_cmdline(int pid, char comm[])
-{
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-
-	__trace_find_cmdline(pid, comm);
-
-	arch_spin_unlock(&trace_cmdline_lock);
-	preempt_enable();
-}
-
-static int *trace_find_tgid_ptr(int pid)
-{
-	/*
-	 * Pairs with the smp_store_release in set_tracer_flag() to ensure that
-	 * if we observe a non-NULL tgid_map then we also observe the correct
-	 * tgid_map_max.
-	 */
-	int *map = smp_load_acquire(&tgid_map);
-
-	if (unlikely(!map || pid > tgid_map_max))
-		return NULL;
-
-	return &map[pid];
-}
-
-int trace_find_tgid(int pid)
-{
-	int *ptr = trace_find_tgid_ptr(pid);
-
-	return ptr ? *ptr : 0;
-}
-
-static int trace_save_tgid(struct task_struct *tsk)
-{
-	int *ptr;
-
-	/* treat recording of idle task as a success */
-	if (!tsk->pid)
-		return 1;
-
-	ptr = trace_find_tgid_ptr(tsk->pid);
-	if (!ptr)
-		return 0;
-
-	*ptr = tsk->tgid;
-	return 1;
-}
-
-static bool tracing_record_taskinfo_skip(int flags)
-{
-	if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
-		return true;
-	if (!__this_cpu_read(trace_taskinfo_save))
-		return true;
-	return false;
-}
-
-/**
- * tracing_record_taskinfo - record the task info of a task
- *
- * @task:  task to record
- * @flags: TRACE_RECORD_CMDLINE for recording comm
- *         TRACE_RECORD_TGID for recording tgid
- */
-void tracing_record_taskinfo(struct task_struct *task, int flags)
-{
-	bool done;
-
-	if (tracing_record_taskinfo_skip(flags))
-		return;
-
-	/*
-	 * Record as much task information as possible. If some fail, continue
-	 * to try to record the others.
-	 */
-	done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task);
-	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task);
-
-	/* If recording any information failed, retry again soon. */
-	if (!done)
-		return;
-
-	__this_cpu_write(trace_taskinfo_save, false);
-}
-
-/**
- * tracing_record_taskinfo_sched_switch - record task info for sched_switch
- *
- * @prev: previous task during sched_switch
- * @next: next task during sched_switch
- * @flags: TRACE_RECORD_CMDLINE for recording comm
- *         TRACE_RECORD_TGID for recording tgid
- */
-void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
-					  struct task_struct *next, int flags)
-{
-	bool done;
-
-	if (tracing_record_taskinfo_skip(flags))
-		return;
-
-	/*
-	 * Record as much task information as possible. If some fail, continue
-	 * to try to record the others.
-	 */
-	done  = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev);
-	done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next);
-	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev);
-	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next);
-
-	/* If recording any information failed, retry again soon. */
-	if (!done)
-		return;
-
-	__this_cpu_write(trace_taskinfo_save, false);
-}
-
-/* Helpers to record a specific task information */
-void tracing_record_cmdline(struct task_struct *task)
-{
-	tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE);
-}
-
-void tracing_record_tgid(struct task_struct *task)
-{
-	tracing_record_taskinfo(task, TRACE_RECORD_TGID);
-}
-
 /*
  * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq
  * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function
@@ -4389,7 +4164,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	get_total_entries(buf, &total, &entries);
 
 	seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
-		   name, UTS_RELEASE);
+		   name, init_utsname()->release);
 	seq_puts(m, "# -----------------------------------"
 		 "---------------------------------\n");
 	seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |"
@@ -5457,8 +5232,6 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set)
 
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
-	int *map;
-
 	if ((mask == TRACE_ITER_RECORD_TGID) ||
 	    (mask == TRACE_ITER_RECORD_CMD))
 		lockdep_assert_held(&event_mutex);
@@ -5481,20 +5254,8 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 		trace_event_enable_cmd_record(enabled);
 
 	if (mask == TRACE_ITER_RECORD_TGID) {
-		if (!tgid_map) {
-			tgid_map_max = pid_max;
-			map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map),
-				       GFP_KERNEL);
 
-			/*
-			 * Pairs with smp_load_acquire() in
-			 * trace_find_tgid_ptr() to ensure that if it observes
-			 * the tgid_map we just allocated then it also observes
-			 * the corresponding tgid_map_max value.
-			 */
-			smp_store_release(&tgid_map, map);
-		}
-		if (!tgid_map) {
+		if (trace_alloc_tgid_map() < 0) {
 			tr->trace_flags &= ~TRACE_ITER_RECORD_TGID;
 			return -ENOMEM;
 		}
@@ -5938,207 +5699,6 @@ static const struct file_operations tracing_readme_fops = {
 	.llseek		= generic_file_llseek,
 };
 
-static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	int pid = ++(*pos);
-
-	return trace_find_tgid_ptr(pid);
-}
-
-static void *saved_tgids_start(struct seq_file *m, loff_t *pos)
-{
-	int pid = *pos;
-
-	return trace_find_tgid_ptr(pid);
-}
-
-static void saved_tgids_stop(struct seq_file *m, void *v)
-{
-}
-
-static int saved_tgids_show(struct seq_file *m, void *v)
-{
-	int *entry = (int *)v;
-	int pid = entry - tgid_map;
-	int tgid = *entry;
-
-	if (tgid == 0)
-		return SEQ_SKIP;
-
-	seq_printf(m, "%d %d\n", pid, tgid);
-	return 0;
-}
-
-static const struct seq_operations tracing_saved_tgids_seq_ops = {
-	.start		= saved_tgids_start,
-	.stop		= saved_tgids_stop,
-	.next		= saved_tgids_next,
-	.show		= saved_tgids_show,
-};
-
-static int tracing_saved_tgids_open(struct inode *inode, struct file *filp)
-{
-	int ret;
-
-	ret = tracing_check_open_get_tr(NULL);
-	if (ret)
-		return ret;
-
-	return seq_open(filp, &tracing_saved_tgids_seq_ops);
-}
-
-
-static const struct file_operations tracing_saved_tgids_fops = {
-	.open		= tracing_saved_tgids_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	unsigned int *ptr = v;
-
-	if (*pos || m->count)
-		ptr++;
-
-	(*pos)++;
-
-	for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num];
-	     ptr++) {
-		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
-			continue;
-
-		return ptr;
-	}
-
-	return NULL;
-}
-
-static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
-{
-	void *v;
-	loff_t l = 0;
-
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-
-	v = &savedcmd->map_cmdline_to_pid[0];
-	while (l <= *pos) {
-		v = saved_cmdlines_next(m, v, &l);
-		if (!v)
-			return NULL;
-	}
-
-	return v;
-}
-
-static void saved_cmdlines_stop(struct seq_file *m, void *v)
-{
-	arch_spin_unlock(&trace_cmdline_lock);
-	preempt_enable();
-}
-
-static int saved_cmdlines_show(struct seq_file *m, void *v)
-{
-	char buf[TASK_COMM_LEN];
-	unsigned int *pid = v;
-
-	__trace_find_cmdline(*pid, buf);
-	seq_printf(m, "%d %s\n", *pid, buf);
-	return 0;
-}
-
-static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
-	.start		= saved_cmdlines_start,
-	.next		= saved_cmdlines_next,
-	.stop		= saved_cmdlines_stop,
-	.show		= saved_cmdlines_show,
-};
-
-static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
-{
-	int ret;
-
-	ret = tracing_check_open_get_tr(NULL);
-	if (ret)
-		return ret;
-
-	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
-}
-
-static const struct file_operations tracing_saved_cmdlines_fops = {
-	.open		= tracing_saved_cmdlines_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static ssize_t
-tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
-				 size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	int r;
-
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
-	arch_spin_unlock(&trace_cmdline_lock);
-	preempt_enable();
-
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static int tracing_resize_saved_cmdlines(unsigned int val)
-{
-	struct saved_cmdlines_buffer *s, *savedcmd_temp;
-
-	s = allocate_cmdlines_buffer(val);
-	if (!s)
-		return -ENOMEM;
-
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-	savedcmd_temp = savedcmd;
-	savedcmd = s;
-	arch_spin_unlock(&trace_cmdline_lock);
-	preempt_enable();
-	free_saved_cmdlines_buffer(savedcmd_temp);
-
-	return 0;
-}
-
-static ssize_t
-tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf,
-				  size_t cnt, loff_t *ppos)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
-	if (ret)
-		return ret;
-
-	/* must have at least 1 entry or less than PID_MAX_DEFAULT */
-	if (!val || val > PID_MAX_DEFAULT)
-		return -EINVAL;
-
-	ret = tracing_resize_saved_cmdlines((unsigned int)val);
-	if (ret < 0)
-		return ret;
-
-	*ppos += cnt;
-
-	return cnt;
-}
-
-static const struct file_operations tracing_saved_cmdlines_size_fops = {
-	.open		= tracing_open_generic,
-	.read		= tracing_saved_cmdlines_size_read,
-	.write		= tracing_saved_cmdlines_size_write,
-};
-
 #ifdef CONFIG_TRACE_EVAL_MAP_FILE
 static union trace_eval_map_item *
 update_eval_map(union trace_eval_map_item *ptr)
@@ -6615,11 +6175,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		 */
 		synchronize_rcu();
 		free_snapshot(tr);
+		tracing_disarm_snapshot(tr);
 	}
 
-	if (t->use_max_tr && !tr->allocated_snapshot) {
-		ret = tracing_alloc_snapshot_instance(tr);
-		if (ret < 0)
+	if (!had_max_tr && t->use_max_tr) {
+		ret = tracing_arm_snapshot_locked(tr);
+		if (ret)
 			goto out;
 	}
 #else
@@ -6628,8 +6189,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 	if (t->init) {
 		ret = tracer_init(t, tr);
-		if (ret)
+		if (ret) {
+#ifdef CONFIG_TRACER_MAX_TRACE
+			if (t->use_max_tr)
+				tracing_disarm_snapshot(tr);
+#endif
 			goto out;
+		}
 	}
 
 	tr->current_trace = t;
@@ -7731,10 +7297,11 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		if (tr->allocated_snapshot)
 			ret = resize_buffer_duplicate_size(&tr->max_buffer,
 					&tr->array_buffer, iter->cpu_file);
-		else
-			ret = tracing_alloc_snapshot_instance(tr);
-		if (ret < 0)
+
+		ret = tracing_arm_snapshot_locked(tr);
+		if (ret)
 			break;
+
 		/* Now, we're going to swap */
 		if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
 			local_irq_disable();
@@ -7744,6 +7311,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer,
 						 (void *)tr, 1);
 		}
+		tracing_disarm_snapshot(tr);
 		break;
 	default:
 		if (tr->allocated_snapshot) {
@@ -8875,8 +8443,13 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
 
 	ops = param ? &snapshot_count_probe_ops :  &snapshot_probe_ops;
 
-	if (glob[0] == '!')
-		return unregister_ftrace_function_probe_func(glob+1, tr, ops);
+	if (glob[0] == '!') {
+		ret = unregister_ftrace_function_probe_func(glob+1, tr, ops);
+		if (!ret)
+			tracing_disarm_snapshot(tr);
+
+		return ret;
+	}
 
 	if (!param)
 		goto out_reg;
@@ -8895,12 +8468,13 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
 		return ret;
 
  out_reg:
-	ret = tracing_alloc_snapshot_instance(tr);
+	ret = tracing_arm_snapshot(tr);
 	if (ret < 0)
 		goto out;
 
 	ret = register_ftrace_function_probe(glob, tr, ops, count);
-
+	if (ret < 0)
+		tracing_disarm_snapshot(tr);
  out:
 	return ret < 0 ? ret : 0;
 }
@@ -9707,7 +9281,9 @@ trace_array_create_systems(const char *name, const char *systems)
 	raw_spin_lock_init(&tr->start_lock);
 
 	tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
+#ifdef CONFIG_TRACER_MAX_TRACE
+	spin_lock_init(&tr->snapshot_trigger_lock);
+#endif
 	tr->current_trace = &nop_trace;
 
 	INIT_LIST_HEAD(&tr->systems);
@@ -10272,14 +9848,14 @@ static struct notifier_block trace_die_notifier = {
 static int trace_die_panic_handler(struct notifier_block *self,
 				unsigned long ev, void *unused)
 {
-	if (!ftrace_dump_on_oops)
+	if (!ftrace_dump_on_oops_enabled())
 		return NOTIFY_DONE;
 
 	/* The die notifier requires DIE_OOPS to trigger */
 	if (self == &trace_die_notifier && ev != DIE_OOPS)
 		return NOTIFY_DONE;
 
-	ftrace_dump(ftrace_dump_on_oops);
+	ftrace_dump(DUMP_PARAM);
 
 	return NOTIFY_DONE;
 }
@@ -10320,12 +9896,12 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
-void trace_init_global_iter(struct trace_iterator *iter)
+static void trace_init_iter(struct trace_iterator *iter, struct trace_array *tr)
 {
-	iter->tr = &global_trace;
+	iter->tr = tr;
 	iter->trace = iter->tr->current_trace;
 	iter->cpu_file = RING_BUFFER_ALL_CPUS;
-	iter->array_buffer = &global_trace.array_buffer;
+	iter->array_buffer = &tr->array_buffer;
 
 	if (iter->trace && iter->trace->open)
 		iter->trace->open(iter);
@@ -10345,22 +9921,19 @@ void trace_init_global_iter(struct trace_iterator *iter)
 	iter->fmt_size = STATIC_FMT_BUF_SIZE;
 }
 
-void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
+void trace_init_global_iter(struct trace_iterator *iter)
+{
+	trace_init_iter(iter, &global_trace);
+}
+
+static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_mode)
 {
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
-	static atomic_t dump_running;
-	struct trace_array *tr = &global_trace;
 	unsigned int old_userobj;
 	unsigned long flags;
 	int cnt = 0, cpu;
 
-	/* Only allow one dump user at a time. */
-	if (atomic_inc_return(&dump_running) != 1) {
-		atomic_dec(&dump_running);
-		return;
-	}
-
 	/*
 	 * Always turn off tracing when we dump.
 	 * We don't need to show trace output of what happens
@@ -10369,12 +9942,12 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	 * If the user does a sysrq-z, then they can re-enable
 	 * tracing with echo 1 > tracing_on.
 	 */
-	tracing_off();
+	tracer_tracing_off(tr);
 
 	local_irq_save(flags);
 
 	/* Simulate the iterator */
-	trace_init_global_iter(&iter);
+	trace_init_iter(&iter, tr);
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
@@ -10385,21 +9958,15 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	/* don't look at user memory in panic mode */
 	tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-	switch (oops_dump_mode) {
-	case DUMP_ALL:
-		iter.cpu_file = RING_BUFFER_ALL_CPUS;
-		break;
-	case DUMP_ORIG:
+	if (dump_mode == DUMP_ORIG)
 		iter.cpu_file = raw_smp_processor_id();
-		break;
-	case DUMP_NONE:
-		goto out_enable;
-	default:
-		printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+	else
 		iter.cpu_file = RING_BUFFER_ALL_CPUS;
-	}
 
-	printk(KERN_TRACE "Dumping ftrace buffer:\n");
+	if (tr == &global_trace)
+		printk(KERN_TRACE "Dumping ftrace buffer:\n");
+	else
+		printk(KERN_TRACE "Dumping ftrace instance %s buffer:\n", tr->name);
 
 	/* Did function tracer already get disabled? */
 	if (ftrace_is_dead()) {
@@ -10441,15 +10008,84 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
- out_enable:
 	tr->trace_flags |= old_userobj;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
 	}
-	atomic_dec(&dump_running);
 	local_irq_restore(flags);
 }
+
+static void ftrace_dump_by_param(void)
+{
+	bool first_param = true;
+	char dump_param[MAX_TRACER_SIZE];
+	char *buf, *token, *inst_name;
+	struct trace_array *tr;
+
+	strscpy(dump_param, ftrace_dump_on_oops, MAX_TRACER_SIZE);
+	buf = dump_param;
+
+	while ((token = strsep(&buf, ",")) != NULL) {
+		if (first_param) {
+			first_param = false;
+			if (!strcmp("0", token))
+				continue;
+			else if (!strcmp("1", token)) {
+				ftrace_dump_one(&global_trace, DUMP_ALL);
+				continue;
+			}
+			else if (!strcmp("2", token) ||
+			  !strcmp("orig_cpu", token)) {
+				ftrace_dump_one(&global_trace, DUMP_ORIG);
+				continue;
+			}
+		}
+
+		inst_name = strsep(&token, "=");
+		tr = trace_array_find(inst_name);
+		if (!tr) {
+			printk(KERN_TRACE "Instance %s not found\n", inst_name);
+			continue;
+		}
+
+		if (token && (!strcmp("2", token) ||
+			  !strcmp("orig_cpu", token)))
+			ftrace_dump_one(tr, DUMP_ORIG);
+		else
+			ftrace_dump_one(tr, DUMP_ALL);
+	}
+}
+
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
+{
+	static atomic_t dump_running;
+
+	/* Only allow one dump user at a time. */
+	if (atomic_inc_return(&dump_running) != 1) {
+		atomic_dec(&dump_running);
+		return;
+	}
+
+	switch (oops_dump_mode) {
+	case DUMP_ALL:
+		ftrace_dump_one(&global_trace, DUMP_ALL);
+		break;
+	case DUMP_ORIG:
+		ftrace_dump_one(&global_trace, DUMP_ORIG);
+		break;
+	case DUMP_PARAM:
+		ftrace_dump_by_param();
+		break;
+	case DUMP_NONE:
+		break;
+	default:
+		printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+		ftrace_dump_one(&global_trace, DUMP_ALL);
+	}
+
+	atomic_dec(&dump_running);
+}
 EXPORT_SYMBOL_GPL(ftrace_dump);
 
 #define WRITE_BUFSIZE  4096
@@ -10677,7 +10313,9 @@ __init static int tracer_alloc_buffers(void)
 	global_trace.current_trace = &nop_trace;
 
 	global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
+#ifdef CONFIG_TRACER_MAX_TRACE
+	spin_lock_init(&global_trace.snapshot_trigger_lock);
+#endif
 	ftrace_init_global_array_ops(&global_trace);
 
 	init_trace_flags_index(&global_trace);
@@ -10714,7 +10352,7 @@ __init static int tracer_alloc_buffers(void)
 out_free_pipe_cpumask:
 	free_cpumask_var(global_trace.pipe_cpumask);
 out_free_savedcmd:
-	free_saved_cmdlines_buffer(savedcmd);
+	trace_free_saved_cmdlines_buffer();
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
 out_rm_hp_state:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 00f873910c5d..64450615ca0c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -334,8 +334,8 @@ struct trace_array {
 	 */
 	struct array_buffer	max_buffer;
 	bool			allocated_snapshot;
-#endif
-#ifdef CONFIG_TRACER_MAX_TRACE
+	spinlock_t		snapshot_trigger_lock;
+	unsigned int		snapshot;
 	unsigned long		max_latency;
 #ifdef CONFIG_FSNOTIFY
 	struct dentry		*d_max_latency;
@@ -1375,6 +1375,16 @@ static inline void trace_buffer_unlock_commit(struct trace_array *tr,
 	trace_buffer_unlock_commit_regs(tr, buffer, event, trace_ctx, NULL);
 }
 
+DECLARE_PER_CPU(bool, trace_taskinfo_save);
+int trace_save_cmdline(struct task_struct *tsk);
+int trace_create_savedcmd(void);
+int trace_alloc_tgid_map(void);
+void trace_free_saved_cmdlines_buffer(void);
+
+extern const struct file_operations tracing_saved_cmdlines_fops;
+extern const struct file_operations tracing_saved_tgids_fops;
+extern const struct file_operations tracing_saved_cmdlines_size_fops;
+
 DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
 DECLARE_PER_CPU(int, trace_buffered_event_cnt);
 void trace_buffered_event_disable(void);
@@ -1973,12 +1983,16 @@ static inline void trace_event_eval_update(struct trace_eval_map **map, int len)
 #ifdef CONFIG_TRACER_SNAPSHOT
 void tracing_snapshot_instance(struct trace_array *tr);
 int tracing_alloc_snapshot_instance(struct trace_array *tr);
+int tracing_arm_snapshot(struct trace_array *tr);
+void tracing_disarm_snapshot(struct trace_array *tr);
 #else
 static inline void tracing_snapshot_instance(struct trace_array *tr) { }
 static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
 	return 0;
 }
+static inline int tracing_arm_snapshot(struct trace_array *tr) { return 0; }
+static inline void tracing_disarm_snapshot(struct trace_array *tr) { }
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 54d5fa35c90a..811b08439406 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -92,7 +92,6 @@ static void trace_do_benchmark(void)
 	bm_total += delta;
 	bm_totalsq += delta * delta;
 
-
 	if (bm_cnt > 1) {
 		/*
 		 * Apply Welford's method to calculate standard deviation:
@@ -105,7 +104,7 @@ static void trace_do_benchmark(void)
 		stddev = 0;
 
 	delta = bm_total;
-	do_div(delta, bm_cnt);
+	delta = div64_u64(delta, bm_cnt);
 	avg = delta;
 
 	if (stddev > 0) {
@@ -127,7 +126,7 @@ static void trace_do_benchmark(void)
 			seed = stddev;
 			if (!last_seed)
 				break;
-			do_div(seed, last_seed);
+			seed = div64_u64(seed, last_seed);
 			seed += last_seed;
 			do_div(seed, 2);
 		} while (i++ < 10 && last_seed != seed);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b33c3861fbbb..4bec043c8690 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -597,20 +597,12 @@ out:
 	return ret;
 }
 
-/**
- * unregister_trigger - Generic event_command @unreg implementation
- * @glob: The raw string used to register the trigger
- * @test: Trigger-specific data used to find the trigger to remove
- * @file: The trace_event_file associated with the event
- *
- * Common implementation for event trigger unregistration.
- *
- * Usually used directly as the @unreg method in event command
- * implementations.
+/*
+ * True if the trigger was found and unregistered, else false.
  */
-static void unregister_trigger(char *glob,
-			       struct event_trigger_data *test,
-			       struct trace_event_file *file)
+static bool try_unregister_trigger(char *glob,
+				   struct event_trigger_data *test,
+				   struct trace_event_file *file)
 {
 	struct event_trigger_data *data = NULL, *iter;
 
@@ -626,8 +618,32 @@ static void unregister_trigger(char *glob,
 		}
 	}
 
-	if (data && data->ops->free)
-		data->ops->free(data);
+	if (data) {
+		if (data->ops->free)
+			data->ops->free(data);
+
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * unregister_trigger - Generic event_command @unreg implementation
+ * @glob: The raw string used to register the trigger
+ * @test: Trigger-specific data used to find the trigger to remove
+ * @file: The trace_event_file associated with the event
+ *
+ * Common implementation for event trigger unregistration.
+ *
+ * Usually used directly as the @unreg method in event command
+ * implementations.
+ */
+static void unregister_trigger(char *glob,
+			       struct event_trigger_data *test,
+			       struct trace_event_file *file)
+{
+	try_unregister_trigger(glob, test, file);
 }
 
 /*
@@ -1470,12 +1486,23 @@ register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	int ret = tracing_alloc_snapshot_instance(file->tr);
+	int ret = tracing_arm_snapshot(file->tr);
 
 	if (ret < 0)
 		return ret;
 
-	return register_trigger(glob, data, file);
+	ret = register_trigger(glob, data, file);
+	if (ret < 0)
+		tracing_disarm_snapshot(file->tr);
+	return ret;
+}
+
+static void unregister_snapshot_trigger(char *glob,
+					struct event_trigger_data *data,
+					struct trace_event_file *file)
+{
+	if (try_unregister_trigger(glob, data, file))
+		tracing_disarm_snapshot(file->tr);
 }
 
 static int
@@ -1510,7 +1537,7 @@ static struct event_command trigger_snapshot_cmd = {
 	.trigger_type		= ETT_SNAPSHOT,
 	.parse			= event_trigger_parse,
 	.reg			= register_snapshot_trigger,
-	.unreg			= unregister_trigger,
+	.unreg			= unregister_snapshot_trigger,
 	.get_trigger_ops	= snapshot_get_trigger_ops,
 	.set_filter		= set_trigger_filter,
 };
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index e76f5e1efdf2..70d428c394b6 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -34,7 +34,8 @@
 
 /* Limit how long of an event name plus args within the subsystem. */
 #define MAX_EVENT_DESC 512
-#define EVENT_NAME(user_event) ((user_event)->tracepoint.name)
+#define EVENT_NAME(user_event) ((user_event)->reg_name)
+#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name)
 #define MAX_FIELD_ARRAY_SIZE 1024
 
 /*
@@ -54,10 +55,13 @@
  * allows isolation for events by various means.
  */
 struct user_event_group {
-	char		*system_name;
-	struct		hlist_node node;
-	struct		mutex reg_mutex;
+	char			*system_name;
+	char			*system_multi_name;
+	struct hlist_node	node;
+	struct mutex		reg_mutex;
 	DECLARE_HASHTABLE(register_table, 8);
+	/* ID that moves forward within the group for multi-event names */
+	u64			multi_id;
 };
 
 /* Group for init_user_ns mapping, top-most group */
@@ -78,6 +82,7 @@ static unsigned int current_user_events;
  */
 struct user_event {
 	struct user_event_group		*group;
+	char				*reg_name;
 	struct tracepoint		tracepoint;
 	struct trace_event_call		call;
 	struct trace_event_class	class;
@@ -127,6 +132,8 @@ struct user_event_enabler {
 
 #define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK))
 
+#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT)
+
 /* Used for asynchronous faulting in of pages */
 struct user_event_enabler_fault {
 	struct work_struct		work;
@@ -202,6 +209,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm);
 static struct user_event_mm *user_event_mm_get_all(struct user_event *user);
 static void user_event_mm_put(struct user_event_mm *mm);
 static int destroy_user_event(struct user_event *user);
+static bool user_fields_match(struct user_event *user, int argc,
+			      const char **argv);
 
 static u32 user_event_key(char *name)
 {
@@ -328,6 +337,7 @@ out:
 static void user_event_group_destroy(struct user_event_group *group)
 {
 	kfree(group->system_name);
+	kfree(group->system_multi_name);
 	kfree(group);
 }
 
@@ -346,6 +356,11 @@ static char *user_event_group_system_name(void)
 	return system_name;
 }
 
+static char *user_event_group_system_multi_name(void)
+{
+	return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL);
+}
+
 static struct user_event_group *current_user_event_group(void)
 {
 	return init_group;
@@ -365,6 +380,11 @@ static struct user_event_group *user_event_group_create(void)
 	if (!group->system_name)
 		goto error;
 
+	group->system_multi_name = user_event_group_system_multi_name();
+
+	if (!group->system_multi_name)
+		goto error;
+
 	mutex_init(&group->reg_mutex);
 	hash_init(group->register_table);
 
@@ -1480,6 +1500,11 @@ static int destroy_user_event(struct user_event *user)
 	hash_del(&user->node);
 
 	user_event_destroy_validators(user);
+
+	/* If we have different names, both must be freed */
+	if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+		kfree(EVENT_TP_NAME(user));
+
 	kfree(user->call.print_fmt);
 	kfree(EVENT_NAME(user));
 	kfree(user);
@@ -1493,17 +1518,36 @@ static int destroy_user_event(struct user_event *user)
 }
 
 static struct user_event *find_user_event(struct user_event_group *group,
-					  char *name, u32 *outkey)
+					  char *name, int argc, const char **argv,
+					  u32 flags, u32 *outkey)
 {
 	struct user_event *user;
 	u32 key = user_event_key(name);
 
 	*outkey = key;
 
-	hash_for_each_possible(group->register_table, user, node, key)
-		if (!strcmp(EVENT_NAME(user), name))
+	hash_for_each_possible(group->register_table, user, node, key) {
+		/*
+		 * Single-format events shouldn't return multi-format
+		 * events. Callers expect the underlying tracepoint to match
+		 * the name exactly in these cases. Only check like-formats.
+		 */
+		if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags))
+			continue;
+
+		if (strcmp(EVENT_NAME(user), name))
+			continue;
+
+		if (user_fields_match(user, argc, argv))
 			return user_event_get(user);
 
+		/* Scan others if this is a multi-format event */
+		if (EVENT_MULTI_FORMAT(flags))
+			continue;
+
+		return ERR_PTR(-EADDRINUSE);
+	}
+
 	return NULL;
 }
 
@@ -1860,6 +1904,9 @@ static bool user_fields_match(struct user_event *user, int argc,
 	struct list_head *head = &user->fields;
 	int i = 0;
 
+	if (argc == 0)
+		return list_empty(head);
+
 	list_for_each_entry_reverse(field, head, link) {
 		if (!user_field_match(field, argc, argv, &i))
 			return false;
@@ -1877,13 +1924,15 @@ static bool user_event_match(const char *system, const char *event,
 	struct user_event *user = container_of(ev, struct user_event, devent);
 	bool match;
 
-	match = strcmp(EVENT_NAME(user), event) == 0 &&
-		(!system || strcmp(system, USER_EVENTS_SYSTEM) == 0);
+	match = strcmp(EVENT_NAME(user), event) == 0;
+
+	if (match && system) {
+		match = strcmp(system, user->group->system_name) == 0 ||
+			strcmp(system, user->group->system_multi_name) == 0;
+	}
 
-	if (match && argc > 0)
+	if (match)
 		match = user_fields_match(user, argc, argv);
-	else if (match && argc == 0)
-		match = list_empty(&user->fields);
 
 	return match;
 }
@@ -1913,6 +1962,33 @@ static int user_event_trace_register(struct user_event *user)
 	return ret;
 }
 
+static int user_event_set_tp_name(struct user_event *user)
+{
+	lockdep_assert_held(&user->group->reg_mutex);
+
+	if (EVENT_MULTI_FORMAT(user->reg_flags)) {
+		char *multi_name;
+
+		multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx",
+				       user->reg_name, user->group->multi_id);
+
+		if (!multi_name)
+			return -ENOMEM;
+
+		user->call.name = multi_name;
+		user->tracepoint.name = multi_name;
+
+		/* Inc to ensure unique multi-event name next time */
+		user->group->multi_id++;
+	} else {
+		/* Non Multi-format uses register name */
+		user->call.name = user->reg_name;
+		user->tracepoint.name = user->reg_name;
+	}
+
+	return 0;
+}
+
 /*
  * Parses the event name, arguments and flags then registers if successful.
  * The name buffer lifetime is owned by this method for success cases only.
@@ -1922,11 +1998,11 @@ static int user_event_parse(struct user_event_group *group, char *name,
 			    char *args, char *flags,
 			    struct user_event **newuser, int reg_flags)
 {
-	int ret;
-	u32 key;
 	struct user_event *user;
+	char **argv = NULL;
 	int argc = 0;
-	char **argv;
+	int ret;
+	u32 key;
 
 	/* Currently don't support any text based flags */
 	if (flags != NULL)
@@ -1935,41 +2011,34 @@ static int user_event_parse(struct user_event_group *group, char *name,
 	if (!user_event_capable(reg_flags))
 		return -EPERM;
 
+	if (args) {
+		argv = argv_split(GFP_KERNEL, args, &argc);
+
+		if (!argv)
+			return -ENOMEM;
+	}
+
 	/* Prevent dyn_event from racing */
 	mutex_lock(&event_mutex);
-	user = find_user_event(group, name, &key);
+	user = find_user_event(group, name, argc, (const char **)argv,
+			       reg_flags, &key);
 	mutex_unlock(&event_mutex);
 
-	if (user) {
-		if (args) {
-			argv = argv_split(GFP_KERNEL, args, &argc);
-			if (!argv) {
-				ret = -ENOMEM;
-				goto error;
-			}
+	if (argv)
+		argv_free(argv);
 
-			ret = user_fields_match(user, argc, (const char **)argv);
-			argv_free(argv);
-
-		} else
-			ret = list_empty(&user->fields);
-
-		if (ret) {
-			*newuser = user;
-			/*
-			 * Name is allocated by caller, free it since it already exists.
-			 * Caller only worries about failure cases for freeing.
-			 */
-			kfree(name);
-		} else {
-			ret = -EADDRINUSE;
-			goto error;
-		}
+	if (IS_ERR(user))
+		return PTR_ERR(user);
+
+	if (user) {
+		*newuser = user;
+		/*
+		 * Name is allocated by caller, free it since it already exists.
+		 * Caller only worries about failure cases for freeing.
+		 */
+		kfree(name);
 
 		return 0;
-error:
-		user_event_put(user, false);
-		return ret;
 	}
 
 	user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT);
@@ -1982,7 +2051,13 @@ error:
 	INIT_LIST_HEAD(&user->validators);
 
 	user->group = group;
-	user->tracepoint.name = name;
+	user->reg_name = name;
+	user->reg_flags = reg_flags;
+
+	ret = user_event_set_tp_name(user);
+
+	if (ret)
+		goto put_user;
 
 	ret = user_event_parse_fields(user, args);
 
@@ -1996,11 +2071,14 @@ error:
 
 	user->call.data = user;
 	user->call.class = &user->class;
-	user->call.name = name;
 	user->call.flags = TRACE_EVENT_FL_TRACEPOINT;
 	user->call.tp = &user->tracepoint;
 	user->call.event.funcs = &user_event_funcs;
-	user->class.system = group->system_name;
+
+	if (EVENT_MULTI_FORMAT(user->reg_flags))
+		user->class.system = group->system_multi_name;
+	else
+		user->class.system = group->system_name;
 
 	user->class.fields_array = user_event_fields_array;
 	user->class.get_fields = user_event_get_fields;
@@ -2022,8 +2100,6 @@ error:
 	if (ret)
 		goto put_user_lock;
 
-	user->reg_flags = reg_flags;
-
 	if (user->reg_flags & USER_EVENT_REG_PERSIST) {
 		/* Ensure we track self ref and caller ref (2) */
 		refcount_set(&user->refcnt, 2);
@@ -2047,30 +2123,43 @@ put_user:
 	user_event_destroy_fields(user);
 	user_event_destroy_validators(user);
 	kfree(user->call.print_fmt);
+
+	/* Caller frees reg_name on error, but not multi-name */
+	if (EVENT_NAME(user) != EVENT_TP_NAME(user))
+		kfree(EVENT_TP_NAME(user));
+
 	kfree(user);
 	return ret;
 }
 
 /*
- * Deletes a previously created event if it is no longer being used.
+ * Deletes previously created events if they are no longer being used.
  */
 static int delete_user_event(struct user_event_group *group, char *name)
 {
-	u32 key;
-	struct user_event *user = find_user_event(group, name, &key);
+	struct user_event *user;
+	struct hlist_node *tmp;
+	u32 key = user_event_key(name);
+	int ret = -ENOENT;
 
-	if (!user)
-		return -ENOENT;
+	/* Attempt to delete all event(s) with the name passed in */
+	hash_for_each_possible_safe(group->register_table, user, tmp, node, key) {
+		if (strcmp(EVENT_NAME(user), name))
+			continue;
 
-	user_event_put(user, true);
+		if (!user_event_last_ref(user))
+			return -EBUSY;
 
-	if (!user_event_last_ref(user))
-		return -EBUSY;
+		if (!user_event_capable(user->reg_flags))
+			return -EPERM;
 
-	if (!user_event_capable(user->reg_flags))
-		return -EPERM;
+		ret = destroy_user_event(user);
 
-	return destroy_user_event(user);
+		if (ret)
+			goto out;
+	}
+out:
+	return ret;
 }
 
 /*
@@ -2628,7 +2717,7 @@ static int user_seq_show(struct seq_file *m, void *p)
 	hash_for_each(group->register_table, i, user, node) {
 		status = user->status;
 
-		seq_printf(m, "%s", EVENT_NAME(user));
+		seq_printf(m, "%s", EVENT_TP_NAME(user));
 
 		if (status != 0)
 			seq_puts(m, " #");
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index c9ffdcfe622e..8a407adb0e1c 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
+#include <linux/kmemleak.h>
 #include <linux/ftrace.h>
 #include <trace/events/sched.h>
 
@@ -148,3 +149,517 @@ void tracing_stop_tgid_record(void)
 {
 	tracing_stop_sched_switch(RECORD_TGID);
 }
+
+/*
+ * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
+ * is the tgid last observed corresponding to pid=i.
+ */
+static int *tgid_map;
+
+/* The maximum valid index into tgid_map. */
+static size_t tgid_map_max;
+
+#define SAVED_CMDLINES_DEFAULT 128
+#define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
+static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+struct saved_cmdlines_buffer {
+	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+	unsigned *map_cmdline_to_pid;
+	unsigned cmdline_num;
+	int cmdline_idx;
+	char saved_cmdlines[];
+};
+static struct saved_cmdlines_buffer *savedcmd;
+
+/* Holds the size of a cmdline and pid element */
+#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s)			\
+	(TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0]))
+
+static inline char *get_saved_cmdlines(int idx)
+{
+	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
+}
+
+static inline void set_cmdline(int idx, const char *cmdline)
+{
+	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+}
+
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+	kmemleak_free(s);
+	free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s;
+	struct page *page;
+	int orig_size, size;
+	int order;
+
+	/* Figure out how much is needed to hold the given number of cmdlines */
+	orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
+	order = get_order(orig_size);
+	size = 1 << (order + PAGE_SHIFT);
+	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		return NULL;
+
+	s = page_address(page);
+	kmemleak_alloc(s, size, 1, GFP_KERNEL);
+	memset(s, 0, sizeof(*s));
+
+	/* Round up to actual allocation */
+	val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
+	s->cmdline_num = val;
+
+	/* Place map_cmdline_to_pid array right after saved_cmdlines */
+	s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
+
+	s->cmdline_idx = 0;
+	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
+	       sizeof(s->map_pid_to_cmdline));
+	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
+	       val * sizeof(*s->map_cmdline_to_pid));
+
+	return s;
+}
+
+int trace_create_savedcmd(void)
+{
+	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
+
+	return savedcmd ? 0 : -ENOMEM;
+}
+
+int trace_save_cmdline(struct task_struct *tsk)
+{
+	unsigned tpid, idx;
+
+	/* treat recording of idle task as a success */
+	if (!tsk->pid)
+		return 1;
+
+	tpid = tsk->pid & (PID_MAX_DEFAULT - 1);
+
+	/*
+	 * It's not the end of the world if we don't get
+	 * the lock, but we also don't want to spin
+	 * nor do we want to disable interrupts,
+	 * so if we miss here, then better luck next time.
+	 *
+	 * This is called within the scheduler and wake up, so interrupts
+	 * had better been disabled and run queue lock been held.
+	 */
+	lockdep_assert_preemption_disabled();
+	if (!arch_spin_trylock(&trace_cmdline_lock))
+		return 0;
+
+	idx = savedcmd->map_pid_to_cmdline[tpid];
+	if (idx == NO_CMDLINE_MAP) {
+		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
+
+		savedcmd->map_pid_to_cmdline[tpid] = idx;
+		savedcmd->cmdline_idx = idx;
+	}
+
+	savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
+	set_cmdline(idx, tsk->comm);
+
+	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
+}
+
+static void __trace_find_cmdline(int pid, char comm[])
+{
+	unsigned map;
+	int tpid;
+
+	if (!pid) {
+		strcpy(comm, "<idle>");
+		return;
+	}
+
+	if (WARN_ON_ONCE(pid < 0)) {
+		strcpy(comm, "<XXX>");
+		return;
+	}
+
+	tpid = pid & (PID_MAX_DEFAULT - 1);
+	map = savedcmd->map_pid_to_cmdline[tpid];
+	if (map != NO_CMDLINE_MAP) {
+		tpid = savedcmd->map_cmdline_to_pid[map];
+		if (tpid == pid) {
+			strscpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN);
+			return;
+		}
+	}
+	strcpy(comm, "<...>");
+}
+
+void trace_find_cmdline(int pid, char comm[])
+{
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	__trace_find_cmdline(pid, comm);
+
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+}
+
+static int *trace_find_tgid_ptr(int pid)
+{
+	/*
+	 * Pairs with the smp_store_release in set_tracer_flag() to ensure that
+	 * if we observe a non-NULL tgid_map then we also observe the correct
+	 * tgid_map_max.
+	 */
+	int *map = smp_load_acquire(&tgid_map);
+
+	if (unlikely(!map || pid > tgid_map_max))
+		return NULL;
+
+	return &map[pid];
+}
+
+int trace_find_tgid(int pid)
+{
+	int *ptr = trace_find_tgid_ptr(pid);
+
+	return ptr ? *ptr : 0;
+}
+
+static int trace_save_tgid(struct task_struct *tsk)
+{
+	int *ptr;
+
+	/* treat recording of idle task as a success */
+	if (!tsk->pid)
+		return 1;
+
+	ptr = trace_find_tgid_ptr(tsk->pid);
+	if (!ptr)
+		return 0;
+
+	*ptr = tsk->tgid;
+	return 1;
+}
+
+static bool tracing_record_taskinfo_skip(int flags)
+{
+	if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
+		return true;
+	if (!__this_cpu_read(trace_taskinfo_save))
+		return true;
+	return false;
+}
+
+/**
+ * tracing_record_taskinfo - record the task info of a task
+ *
+ * @task:  task to record
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ *         TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo(struct task_struct *task, int flags)
+{
+	bool done;
+
+	if (tracing_record_taskinfo_skip(flags))
+		return;
+
+	/*
+	 * Record as much task information as possible. If some fail, continue
+	 * to try to record the others.
+	 */
+	done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task);
+	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task);
+
+	/* If recording any information failed, retry again soon. */
+	if (!done)
+		return;
+
+	__this_cpu_write(trace_taskinfo_save, false);
+}
+
+/**
+ * tracing_record_taskinfo_sched_switch - record task info for sched_switch
+ *
+ * @prev: previous task during sched_switch
+ * @next: next task during sched_switch
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ *         TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
+					  struct task_struct *next, int flags)
+{
+	bool done;
+
+	if (tracing_record_taskinfo_skip(flags))
+		return;
+
+	/*
+	 * Record as much task information as possible. If some fail, continue
+	 * to try to record the others.
+	 */
+	done  = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev);
+	done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next);
+	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev);
+	done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next);
+
+	/* If recording any information failed, retry again soon. */
+	if (!done)
+		return;
+
+	__this_cpu_write(trace_taskinfo_save, false);
+}
+
+/* Helpers to record a specific task information */
+void tracing_record_cmdline(struct task_struct *task)
+{
+	tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE);
+}
+
+void tracing_record_tgid(struct task_struct *task)
+{
+	tracing_record_taskinfo(task, TRACE_RECORD_TGID);
+}
+
+int trace_alloc_tgid_map(void)
+{
+	int *map;
+
+	if (tgid_map)
+		return 0;
+
+	tgid_map_max = pid_max;
+	map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map),
+		       GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	/*
+	 * Pairs with smp_load_acquire() in
+	 * trace_find_tgid_ptr() to ensure that if it observes
+	 * the tgid_map we just allocated then it also observes
+	 * the corresponding tgid_map_max value.
+	 */
+	smp_store_release(&tgid_map, map);
+	return 0;
+}
+
+static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	int pid = ++(*pos);
+
+	return trace_find_tgid_ptr(pid);
+}
+
+static void *saved_tgids_start(struct seq_file *m, loff_t *pos)
+{
+	int pid = *pos;
+
+	return trace_find_tgid_ptr(pid);
+}
+
+static void saved_tgids_stop(struct seq_file *m, void *v)
+{
+}
+
+static int saved_tgids_show(struct seq_file *m, void *v)
+{
+	int *entry = (int *)v;
+	int pid = entry - tgid_map;
+	int tgid = *entry;
+
+	if (tgid == 0)
+		return SEQ_SKIP;
+
+	seq_printf(m, "%d %d\n", pid, tgid);
+	return 0;
+}
+
+static const struct seq_operations tracing_saved_tgids_seq_ops = {
+	.start		= saved_tgids_start,
+	.stop		= saved_tgids_stop,
+	.next		= saved_tgids_next,
+	.show		= saved_tgids_show,
+};
+
+static int tracing_saved_tgids_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
+
+	return seq_open(filp, &tracing_saved_tgids_seq_ops);
+}
+
+
+const struct file_operations tracing_saved_tgids_fops = {
+	.open		= tracing_saved_tgids_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	unsigned int *ptr = v;
+
+	if (*pos || m->count)
+		ptr++;
+
+	(*pos)++;
+
+	for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num];
+	     ptr++) {
+		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
+			continue;
+
+		return ptr;
+	}
+
+	return NULL;
+}
+
+static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
+{
+	void *v;
+	loff_t l = 0;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	v = &savedcmd->map_cmdline_to_pid[0];
+	while (l <= *pos) {
+		v = saved_cmdlines_next(m, v, &l);
+		if (!v)
+			return NULL;
+	}
+
+	return v;
+}
+
+static void saved_cmdlines_stop(struct seq_file *m, void *v)
+{
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+}
+
+static int saved_cmdlines_show(struct seq_file *m, void *v)
+{
+	char buf[TASK_COMM_LEN];
+	unsigned int *pid = v;
+
+	__trace_find_cmdline(*pid, buf);
+	seq_printf(m, "%d %s\n", *pid, buf);
+	return 0;
+}
+
+static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
+	.start		= saved_cmdlines_start,
+	.next		= saved_cmdlines_next,
+	.stop		= saved_cmdlines_stop,
+	.show		= saved_cmdlines_show,
+};
+
+static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
+
+	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
+}
+
+const struct file_operations tracing_saved_cmdlines_fops = {
+	.open		= tracing_saved_cmdlines_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static ssize_t
+tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
+				 size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int r;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+void trace_free_saved_cmdlines_buffer(void)
+{
+	free_saved_cmdlines_buffer(savedcmd);
+}
+
+static int tracing_resize_saved_cmdlines(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s, *savedcmd_temp;
+
+	s = allocate_cmdlines_buffer(val);
+	if (!s)
+		return -ENOMEM;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+	savedcmd_temp = savedcmd;
+	savedcmd = s;
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+	free_saved_cmdlines_buffer(savedcmd_temp);
+
+	return 0;
+}
+
+static ssize_t
+tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	/* must have at least 1 entry or less than PID_MAX_DEFAULT */
+	if (!val || val > PID_MAX_DEFAULT)
+		return -EINVAL;
+
+	ret = tracing_resize_saved_cmdlines((unsigned int)val);
+	if (ret < 0)
+		return ret;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+const struct file_operations tracing_saved_cmdlines_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_saved_cmdlines_size_read,
+	.write		= tracing_saved_cmdlines_size_write,
+};
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 529590499b1f..e9c5058a8efd 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -768,7 +768,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
 		ftrace_graph_stop();
 		printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
-		if (ftrace_dump_on_oops) {
+		if (ftrace_dump_on_oops_enabled()) {
 			ftrace_dump(DUMP_ALL);
 			/* ftrace_dump() disables tracing */
 			tracing_on();