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
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1572,12 +1572,28 @@
 			The above will cause the "foo" tracing instance to trigger
 			a snapshot at the end of boot up.
 
-	ftrace_dump_on_oops[=orig_cpu]
+	ftrace_dump_on_oops[=2(orig_cpu) | =<instance>][,<instance> |
+			  ,<instance>=2(orig_cpu)]
 			[FTRACE] will dump the trace buffers on oops.
-			If no parameter is passed, ftrace will dump
-			buffers of all CPUs, but if you pass orig_cpu, it will
-			dump only the buffer of the CPU that triggered the
-			oops.
+			If no parameter is passed, ftrace will dump global
+			buffers of all CPUs, if you pass 2 or orig_cpu, it
+			will dump only the buffer of the CPU that triggered
+			the oops, or the specific instance will be dumped if
+			its name is passed. Multiple instance dump is also
+			supported, and instances are separated by commas. Each
+			instance supports only dump on CPU that triggered the
+			oops by passing 2 or orig_cpu to it.
+
+			ftrace_dump_on_oops=foo=orig_cpu
+
+			The above will dump only the buffer of "foo" instance
+			on CPU that triggered the oops.
+
+			ftrace_dump_on_oops,foo,bar=orig_cpu
+
+			The above will dump global buffer on all CPUs, the
+			buffer of "foo" instance on all CPUs and the buffer
+			of "bar" instance on CPU that triggered the oops.
 
 	ftrace_filter=[function-list]
 			[FTRACE] Limit the functions traced by the function

Documentation/admin-guide/sysctl/kernel.rst

@@ -296,12 +296,30 @@ kernel panic). This will output the contents of the ftrace buffers to
 the console.  This is very useful for capturing traces that lead to
 crashes and outputting them to a serial console.
 
-= ===================================================
-0 Disabled (default).
-1 Dump buffers of all CPUs.
-2 Dump the buffer of the CPU that triggered the oops.
-= ===================================================
+======================= ===========================================
+0                       Disabled (default).
+1                       Dump buffers of all CPUs.
+2(orig_cpu)             Dump the buffer of the CPU that triggered the
+                        oops.
+<instance>              Dump the specific instance buffer on all CPUs.
+<instance>=2(orig_cpu)  Dump the specific instance buffer on the CPU
+                        that triggered the oops.
+======================= ===========================================
 
+Multiple instance dump is also supported, and instances are separated
+by commas. If global buffer also needs to be dumped, please specify
+the dump mode (1/2/orig_cpu) first for global buffer.
+
+So for example to dump "foo" and "bar" instance buffer on all CPUs,
+user can::
+
+  echo "foo,bar" > /proc/sys/kernel/ftrace_dump_on_oops
+
+To dump global buffer and "foo" instance buffer on all
+CPUs along with the "bar" instance buffer on CPU that triggered the
+oops, user can::
+
+  echo "1,foo,bar=2" > /proc/sys/kernel/ftrace_dump_on_oops
 
 ftrace_enabled, stack_tracer_enabled
 ====================================

Documentation/trace/user_events.rst

@@ -92,6 +92,24 @@ The following flags are currently supported.
   process closes or unregisters the event. Requires CAP_PERFMON otherwise
   -EPERM is returned.
 
++ USER_EVENT_REG_MULTI_FORMAT: The event can contain multiple formats. This
+  allows programs to prevent themselves from being blocked when their event
+  format changes and they wish to use the same name. When this flag is used the
+  tracepoint name will be in the new format of "name.unique_id" vs the older
+  format of "name". A tracepoint will be created for each unique pair of name
+  and format. This means if several processes use the same name and format,
+  they will use the same tracepoint. If yet another process uses the same name,
+  but a different format than the other processes, it will use a different
+  tracepoint with a new unique id. Recording programs need to scan tracefs for
+  the various different formats of the event name they are interested in
+  recording. The system name of the tracepoint will also use "user_events_multi"
+  instead of "user_events". This prevents single-format event names conflicting
+  with any multi-format event names within tracefs. The unique_id is output as
+  a hex string. Recording programs should ensure the tracepoint name starts with
+  the event name they registered and has a suffix that starts with . and only
+  has hex characters. For example to find all versions of the event "test" you
+  can use the regex "^test\.[0-9a-fA-F]+$".
+
 Upon successful registration the following is set.
 
 + write_index: The index to use for this file descriptor that represents this
@@ -106,6 +124,9 @@ or perf record -e user_events:[name] when attaching/recording.
 **NOTE:** The event subsystem name by default is "user_events". Callers should
 not assume it will always be "user_events". Operators reserve the right in the
 future to change the subsystem name per-process to accommodate event isolation.
+In addition if the USER_EVENT_REG_MULTI_FORMAT flag is used the tracepoint name
+will have a unique id appended to it and the system name will be
+"user_events_multi" as described above.
 
 Command Format
 ^^^^^^^^^^^^^^
@@ -156,7 +177,11 @@ to request deletes than the one used for registration due to this.
 to the event. If programs do not want auto-delete, they must use the
 USER_EVENT_REG_PERSIST flag when registering the event. Once that flag is used
 the event exists until DIAG_IOCSDEL is invoked. Both register and delete of an
-event that persists requires CAP_PERFMON, otherwise -EPERM is returned.
+event that persists requires CAP_PERFMON, otherwise -EPERM is returned. When
+there are multiple formats of the same event name, all events with the same
+name will be attempted to be deleted. If only a specific version is wanted to
+be deleted then the /sys/kernel/tracing/dynamic_events file should be used for
+that specific format of the event.
 
 Unregistering
 -------------

drivers/cxl/core/trace.h

@@ -646,18 +646,18 @@ u64 cxl_trace_hpa(struct cxl_region *cxlr, struct cxl_memdev *memdev, u64 dpa);
 
 TRACE_EVENT(cxl_poison,
 
-	TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region,
+	TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *cxlr,
 		 const struct cxl_poison_record *record, u8 flags,
 		 __le64 overflow_ts, enum cxl_poison_trace_type trace_type),
 
-	TP_ARGS(cxlmd, region, record, flags, overflow_ts, trace_type),
+	TP_ARGS(cxlmd, cxlr, record, flags, overflow_ts, trace_type),
 
 	TP_STRUCT__entry(
 		__string(memdev, dev_name(&cxlmd->dev))
 		__string(host, dev_name(cxlmd->dev.parent))
 		__field(u64, serial)
 		__field(u8, trace_type)
-		__string(region, region)
+		__string(region, cxlr ? dev_name(&cxlr->dev) : "")
 		__field(u64, overflow_ts)
 		__field(u64, hpa)
 		__field(u64, dpa)
@@ -677,10 +677,10 @@ TRACE_EVENT(cxl_poison,
 		__entry->source = cxl_poison_record_source(record);
 		__entry->trace_type = trace_type;
 		__entry->flags = flags;
-		if (region) {
-			__assign_str(region, dev_name(&region->dev));
-			memcpy(__entry->uuid, &region->params.uuid, 16);
-			__entry->hpa = cxl_trace_hpa(region, cxlmd,
+		if (cxlr) {
+			__assign_str(region, dev_name(&cxlr->dev));
+			memcpy(__entry->uuid, &cxlr->params.uuid, 16);
+			__entry->hpa = cxl_trace_hpa(cxlr, cxlmd,
 						     __entry->dpa);
 		} else {
 			__assign_str(region, "");

drivers/gpu/drm/i915/display/intel_display_trace.h

@@ -411,7 +411,7 @@ TRACE_EVENT(intel_fbc_activate,
 			   struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev),
 									 plane->pipe);
 			   __assign_str(dev, __dev_name_kms(plane));
-			   __assign_str(name, plane->base.name)
+			   __assign_str(name, plane->base.name);
 			   __entry->pipe = crtc->pipe;
 			   __entry->frame = intel_crtc_get_vblank_counter(crtc);
 			   __entry->scanline = intel_get_crtc_scanline(crtc);
@@ -438,7 +438,7 @@ TRACE_EVENT(intel_fbc_deactivate,
 			   struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev),
 									 plane->pipe);
 			   __assign_str(dev, __dev_name_kms(plane));
-			   __assign_str(name, plane->base.name)
+			   __assign_str(name, plane->base.name);
 			   __entry->pipe = crtc->pipe;
 			   __entry->frame = intel_crtc_get_vblank_counter(crtc);
 			   __entry->scanline = intel_get_crtc_scanline(crtc);
@@ -465,7 +465,7 @@ TRACE_EVENT(intel_fbc_nuke,
 			   struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev),
 									 plane->pipe);
 			   __assign_str(dev, __dev_name_kms(plane));
-			   __assign_str(name, plane->base.name)
+			   __assign_str(name, plane->base.name);
 			   __entry->pipe = crtc->pipe;
 			   __entry->frame = intel_crtc_get_vblank_counter(crtc);
 			   __entry->scanline = intel_get_crtc_scanline(crtc);

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h

@@ -24,7 +24,7 @@ TRACE_EVENT(hclge_pf_mbx_get,
 		__field(u8, code)
 		__field(u8, subcode)
 		__string(pciname, pci_name(hdev->pdev))
-		__string(devname, &hdev->vport[0].nic.kinfo.netdev->name)
+		__string(devname, hdev->vport[0].nic.kinfo.netdev->name)
 		__array(u32, mbx_data, PF_GET_MBX_LEN)
 	),
 
@@ -33,7 +33,7 @@ TRACE_EVENT(hclge_pf_mbx_get,
 		__entry->code = req->msg.code;
 		__entry->subcode = req->msg.subcode;
 		__assign_str(pciname, pci_name(hdev->pdev));
-		__assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name);
+		__assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name);
 		memcpy(__entry->mbx_data, req,
 		       sizeof(struct hclge_mbx_vf_to_pf_cmd));
 	),
@@ -56,7 +56,7 @@ TRACE_EVENT(hclge_pf_mbx_send,
 		__field(u8, vfid)
 		__field(u16, code)
 		__string(pciname, pci_name(hdev->pdev))
-		__string(devname, &hdev->vport[0].nic.kinfo.netdev->name)
+		__string(devname, hdev->vport[0].nic.kinfo.netdev->name)
 		__array(u32, mbx_data, PF_SEND_MBX_LEN)
 	),
 
@@ -64,7 +64,7 @@ TRACE_EVENT(hclge_pf_mbx_send,
 		__entry->vfid = req->dest_vfid;
 		__entry->code = le16_to_cpu(req->msg.code);
 		__assign_str(pciname, pci_name(hdev->pdev));
-		__assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name);
+		__assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name);
 		memcpy(__entry->mbx_data, req,
 		       sizeof(struct hclge_mbx_pf_to_vf_cmd));
 	),

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h

@@ -23,7 +23,7 @@ TRACE_EVENT(hclge_vf_mbx_get,
 		__field(u8, vfid)
 		__field(u16, code)
 		__string(pciname, pci_name(hdev->pdev))
-		__string(devname, &hdev->nic.kinfo.netdev->name)
+		__string(devname, hdev->nic.kinfo.netdev->name)
 		__array(u32, mbx_data, VF_GET_MBX_LEN)
 	),
 
@@ -31,7 +31,7 @@ TRACE_EVENT(hclge_vf_mbx_get,
 		__entry->vfid = req->dest_vfid;
 		__entry->code = le16_to_cpu(req->msg.code);
 		__assign_str(pciname, pci_name(hdev->pdev));
-		__assign_str(devname, &hdev->nic.kinfo.netdev->name);
+		__assign_str(devname, hdev->nic.kinfo.netdev->name);
 		memcpy(__entry->mbx_data, req,
 		       sizeof(struct hclge_mbx_pf_to_vf_cmd));
 	),
@@ -55,7 +55,7 @@ TRACE_EVENT(hclge_vf_mbx_send,
 		__field(u8, code)
 		__field(u8, subcode)
 		__string(pciname, pci_name(hdev->pdev))
-		__string(devname, &hdev->nic.kinfo.netdev->name)
+		__string(devname, hdev->nic.kinfo.netdev->name)
 		__array(u32, mbx_data, VF_SEND_MBX_LEN)
 	),
 
@@ -64,7 +64,7 @@ TRACE_EVENT(hclge_vf_mbx_send,
 		__entry->code = req->msg.code;
 		__entry->subcode = req->msg.subcode;
 		__assign_str(pciname, pci_name(hdev->pdev));
-		__assign_str(devname, &hdev->nic.kinfo.netdev->name);
+		__assign_str(devname, hdev->nic.kinfo.netdev->name);
 		memcpy(__entry->mbx_data, req,
 		       sizeof(struct hclge_mbx_vf_to_pf_cmd));
 	),

fs/nfsd/trace.h

@@ -104,7 +104,7 @@ TRACE_EVENT(nfsd_compound,
 	TP_fast_assign(
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
 		__entry->opcnt = opcnt;
-		__assign_str_len(tag, tag, taglen);
+		__assign_str(tag, tag);
 	),
 	TP_printk("xid=0x%08x opcnt=%u tag=%s",
 		__entry->xid, __entry->opcnt, __get_str(tag)
@@ -485,7 +485,7 @@ TRACE_EVENT(nfsd_dirent,
 	TP_fast_assign(
 		__entry->fh_hash = fhp ? knfsd_fh_hash(&fhp->fh_handle) : 0;
 		__entry->ino = ino;
-		__assign_str_len(name, name, namlen)
+		__assign_str(name, name);
 	),
 	TP_printk("fh_hash=0x%08x ino=%llu name=%s",
 		__entry->fh_hash, __entry->ino, __get_str(name)
@@ -896,7 +896,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class,
 		__array(unsigned char, addr, sizeof(struct sockaddr_in6))
 		__field(unsigned long, flavor)
 		__array(unsigned char, verifier, NFS4_VERIFIER_SIZE)
-		__string_len(name, name, clp->cl_name.len)
+		__string_len(name, clp->cl_name.data, clp->cl_name.len)
 	),
 	TP_fast_assign(
 		__entry->cl_boot = clp->cl_clientid.cl_boot;
@@ -906,7 +906,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class,
 		__entry->flavor = clp->cl_cred.cr_flavor;
 		memcpy(__entry->verifier, (void *)&clp->cl_verifier,
 		       NFS4_VERIFIER_SIZE);
-		__assign_str_len(name, clp->cl_name.data, clp->cl_name.len);
+		__assign_str(name, clp->cl_name.data);
 	),
 	TP_printk("addr=%pISpc name='%s' verifier=0x%s flavor=%s client=%08x:%08x",
 		__entry->addr, __get_str(name),
@@ -1976,7 +1976,7 @@ TRACE_EVENT(nfsd_ctl_time,
 	TP_fast_assign(
 		__entry->netns_ino = net->ns.inum;
 		__entry->time = time;
-		__assign_str_len(name, name, namelen);
+		__assign_str(name, name);
 	),
 	TP_printk("file=%s time=%d\n",
 		__get_str(name), __entry->time

fs/tracefs/event_inode.c

@@ -35,6 +35,17 @@ static DEFINE_MUTEX(eventfs_mutex);
 /* Choose something "unique" ;-) */
 #define EVENTFS_FILE_INODE_INO		0x12c4e37
 
+struct eventfs_root_inode {
+	struct eventfs_inode		ei;
+	struct dentry			*events_dir;
+};
+
+static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei)
+{
+	WARN_ON_ONCE(!ei->is_events);
+	return container_of(ei, struct eventfs_root_inode, ei);
+}
+
 /* Just try to make something consistent and unique */
 static int eventfs_dir_ino(struct eventfs_inode *ei)
 {
@@ -73,12 +84,18 @@ enum {
 static void release_ei(struct kref *ref)
 {
 	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+	struct eventfs_root_inode *rei;
 
 	WARN_ON_ONCE(!ei->is_freed);
 
 	kfree(ei->entry_attrs);
 	kfree_const(ei->name);
-	kfree_rcu(ei, rcu);
+	if (ei->is_events) {
+		rei = get_root_inode(ei);
+		kfree_rcu(rei, ei.rcu);
+	} else {
+		kfree_rcu(ei, rcu);
+	}
 }
 
 static inline void put_ei(struct eventfs_inode *ei)
@@ -408,19 +425,43 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 	return NULL;
 }
 
+static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char *name)
+{
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name)
+		return NULL;
+	kref_init(&ei->kref);
+	return ei;
+}
+
 static inline struct eventfs_inode *alloc_ei(const char *name)
 {
 	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	struct eventfs_inode *result;
 
 	if (!ei)
 		return NULL;
 
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name) {
+	result = init_ei(ei, name);
+	if (!result)
 		kfree(ei);
+
+	return result;
+}
+
+static inline struct eventfs_inode *alloc_root_ei(const char *name)
+{
+	struct eventfs_root_inode *rei = kzalloc(sizeof(*rei), GFP_KERNEL);
+	struct eventfs_inode *ei;
+
+	if (!rei)
 		return NULL;
-	}
-	kref_init(&ei->kref);
+
+	rei->ei.is_events = 1;
+	ei = init_ei(&rei->ei, name);
+	if (!ei)
+		kfree(rei);
+
 	return ei;
 }
 
@@ -483,7 +524,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
+	if (WARN_ON_ONCE(!(ti->flags & TRACEFS_EVENT_INODE)))
 		return ERR_PTR(-EIO);
 
 	mutex_lock(&eventfs_mutex);
@@ -495,7 +536,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	list_for_each_entry(ei_child, &ei->children, list) {
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		if (ei_child->is_freed)
+		/* A child is freed and removed from the list at the same time */
+		if (WARN_ON_ONCE(ei_child->is_freed))
 			goto out;
 		result = lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
@@ -709,6 +751,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 						int size, void *data)
 {
 	struct dentry *dentry = tracefs_start_creating(name, parent);
+	struct eventfs_root_inode *rei;
 	struct eventfs_inode *ei;
 	struct tracefs_inode *ti;
 	struct inode *inode;
@@ -721,7 +764,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 
-	ei = alloc_ei(name);
+	ei = alloc_root_ei(name);
 	if (!ei)
 		goto fail;
 
@@ -730,10 +773,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 		goto fail;
 
 	// Note: we have a ref to the dentry from tracefs_start_creating()
-	ei->events_dir = dentry;
+	rei = get_root_inode(ei);
+	rei->events_dir = dentry;
+
 	ei->entries = entries;
 	ei->nr_entries = size;
-	ei->is_events = 1;
 	ei->data = data;
 
 	/* Save the ownership of this directory */
@@ -844,13 +888,15 @@ void eventfs_remove_dir(struct eventfs_inode *ei)
  */
 void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
+	struct eventfs_root_inode *rei;
 	struct dentry *dentry;
 
-	dentry = ei->events_dir;
+	rei = get_root_inode(ei);
+	dentry = rei->events_dir;
 	if (!dentry)
 		return;
 
-	ei->events_dir = NULL;
+	rei->events_dir = NULL;
 	eventfs_remove_dir(ei);
 
 	/*

fs/tracefs/internal.h

@@ -36,7 +36,6 @@ struct eventfs_attr {
  * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
  * @data:	The private data to pass to the callbacks
  * @attr:	Saved mode and ownership of eventfs_inode itself
@@ -54,7 +53,6 @@ struct eventfs_inode {
 	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
 	void				*data;
 	struct eventfs_attr		attr;

include/linux/ftrace.h

@@ -1151,7 +1151,9 @@ static inline void unpause_graph_tracing(void) { }
 #ifdef CONFIG_TRACING
 enum ftrace_dump_mode;
 
-extern enum ftrace_dump_mode ftrace_dump_on_oops;
+#define MAX_TRACER_SIZE		100
+extern char ftrace_dump_on_oops[];
+extern int ftrace_dump_on_oops_enabled(void);
 extern int tracepoint_printk;
 
 extern void disable_trace_on_warning(void);

include/linux/kernel.h

@@ -215,6 +215,7 @@ enum ftrace_dump_mode {
 	DUMP_NONE,
 	DUMP_ALL,
 	DUMP_ORIG,
+	DUMP_PARAM,
 };
 
 #ifdef CONFIG_TRACING

include/linux/trace_events.h

@@ -17,6 +17,9 @@ struct dentry;
 struct bpf_prog;
 union bpf_attr;
 
+/* Used for event string fields when they are NULL */
+#define EVENT_NULL_STR		"(null)"
+
 const char *trace_print_flags_seq(struct trace_seq *p, const char *delim,
 				  unsigned long flags,
 				  const struct trace_print_flags *flag_array);

include/linux/tracepoint.h

@@ -199,7 +199,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		if (!(cond))						\
 			return;						\
 									\
-		if (WARN_ON_ONCE(RCUIDLE_COND(rcuidle)))		\
+		if (WARN_ONCE(RCUIDLE_COND(rcuidle),			\
+			      "Bad RCU usage for tracepoint"))		\
 			return;						\
 									\
 		/* keep srcu and sched-rcu usage consistent */		\
@@ -259,7 +260,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 				TP_ARGS(args),				\
 				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
-			WARN_ON_ONCE(!rcu_is_watching());		\
+			WARN_ONCE(!rcu_is_watching(),			\
+				  "RCU not watching for tracepoint");	\
 		}							\
 	}								\
 	__DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args),		\

include/trace/events/sunrpc.h

@@ -1331,18 +1331,18 @@ TRACE_EVENT(xs_stream_read_data,
 		__field(ssize_t, err)
 		__field(size_t, total)
 		__string(addr, xprt ? xprt->address_strings[RPC_DISPLAY_ADDR] :
-				"(null)")
+				EVENT_NULL_STR)
 		__string(port, xprt ? xprt->address_strings[RPC_DISPLAY_PORT] :
-				"(null)")
+				EVENT_NULL_STR)
 	),
 
 	TP_fast_assign(
 		__entry->err = err;
 		__entry->total = total;
 		__assign_str(addr, xprt ?
-			xprt->address_strings[RPC_DISPLAY_ADDR] : "(null)");
+			xprt->address_strings[RPC_DISPLAY_ADDR] : EVENT_NULL_STR);
 		__assign_str(port, xprt ?
-			xprt->address_strings[RPC_DISPLAY_PORT] : "(null)");
+			xprt->address_strings[RPC_DISPLAY_PORT] : EVENT_NULL_STR);
 	),
 
 	TP_printk("peer=[%s]:%s err=%zd total=%zu", __get_str(addr),
@@ -1787,7 +1787,7 @@ TRACE_EVENT(svc_process,
 		__string(service, name)
 		__string(procedure, svc_proc_name(rqst))
 		__string(addr, rqst->rq_xprt ?
-			 rqst->rq_xprt->xpt_remotebuf : "(null)")
+			 rqst->rq_xprt->xpt_remotebuf : EVENT_NULL_STR)
 	),
 
 	TP_fast_assign(
@@ -1797,7 +1797,7 @@ TRACE_EVENT(svc_process,
 		__assign_str(service, name);
 		__assign_str(procedure, svc_proc_name(rqst));
 		__assign_str(addr, rqst->rq_xprt ?
-			     rqst->rq_xprt->xpt_remotebuf : "(null)");
+			     rqst->rq_xprt->xpt_remotebuf : EVENT_NULL_STR);
 	),
 
 	TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%s",

include/trace/stages/stage2_data_offsets.h

@@ -24,7 +24,7 @@
 #define __array(type, item, len)
 
 #undef __dynamic_array
-#define __dynamic_array(type, item, len)	u32 item;
+#define __dynamic_array(type, item, len)	u32 item; const void *item##_ptr_;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
@@ -45,7 +45,7 @@
 #define __sockaddr(field, len) __dynamic_array(u8, field, len)
 
 #undef __rel_dynamic_array
-#define __rel_dynamic_array(type, item, len)	u32 item;
+#define __rel_dynamic_array(type, item, len)	u32 item; const void *item##_ptr_;
 
 #undef __rel_string
 #define __rel_string(item, src) __rel_dynamic_array(char, item, -1)

include/trace/stages/stage5_get_offsets.h

@@ -9,6 +9,16 @@
 #undef __entry
 #define __entry entry
 
+#ifndef __STAGE5_STRING_SRC_H
+#define __STAGE5_STRING_SRC_H
+static inline const char *__string_src(const char *str)
+{
+       if (!str)
+	       return EVENT_NULL_STR;
+       return str;
+}
+#endif /* __STAGE5_STRING_SRC_H */
+
 /*
  * Fields should never declare an array: i.e. __field(int, arr[5])
  * If they do, it will cause issues in parsing and possibly corrupt the
@@ -47,10 +57,12 @@
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item,			\
-		    strlen((src) ? (const char *)(src) : "(null)") + 1)
+		    strlen(__string_src(src)) + 1)			\
+	__data_offsets->item##_ptr_ = src;
 
 #undef __string_len
-#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)
+#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)\
+	__data_offsets->item##_ptr_ = src;
 
 #undef __vstring
 #define __vstring(item, fmt, ap) __dynamic_array(char, item,		\
@@ -67,11 +79,14 @@
 	__data_size += __item_length;
 
 #undef __rel_string
-#define __rel_string(item, src) __rel_dynamic_array(char, item,			\
-		    strlen((src) ? (const char *)(src) : "(null)") + 1)
+#define __rel_string(item, src) __rel_dynamic_array(char, item,		\
+		    strlen(__string_src(src)) + 1)			\
+	__data_offsets->item##_ptr_ = src;
 
 #undef __rel_string_len
-#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)
+#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)\
+	__data_offsets->item##_ptr_ = src;
+
 /*
  * __bitmask_size_in_bytes_raw is the number of bytes needed to hold
  * num_possible_cpus().

include/trace/stages/stage6_event_callback.h

@@ -32,14 +32,16 @@
 
 #undef __assign_str
 #define __assign_str(dst, src)						\
-	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
-
-#undef __assign_str_len
-#define __assign_str_len(dst, src, len)					\
 	do {								\
-		memcpy(__get_str(dst), (src), (len));			\
-		__get_str(dst)[len] = '\0';				\
-	} while(0)
+		char *__str__ = __get_str(dst);				\
+		int __len__ = __get_dynamic_array_len(dst) - 1;		\
+		WARN_ON_ONCE(__builtin_constant_p(src) ?		\
+			     strcmp((src), __data_offsets.dst##_ptr_) :	\
+			     (src) != __data_offsets.dst##_ptr_);	\
+		memcpy(__str__, __data_offsets.dst##_ptr_ ? :		\
+		       EVENT_NULL_STR, __len__);			\
+		__str__[__len__] = '\0';				\
+	} while (0)
 
 #undef __assign_vstr
 #define __assign_vstr(dst, fmt, va)					\
@@ -91,14 +93,13 @@
 #define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1)
 
 #undef __assign_rel_str
-#define __assign_rel_str(dst, src)					\
-	strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)");
-
-#undef __assign_rel_str_len
-#define __assign_rel_str_len(dst, src, len)				\
+#define __assign_rel_str(dst)						\
 	do {								\
-		memcpy(__get_rel_str(dst), (src), (len));		\
-		__get_rel_str(dst)[len] = '\0';				\
+		char *__str__ = __get_rel_str(dst);			\
+		int __len__ = __get_rel_dynamic_array_len(dst) - 1;	\
+		memcpy(__str__, __data_offsets.dst##_ptr_ ? :		\
+		       EVENT_NULL_STR, __len__);			\
+		__str__[__len__] = '\0';				\
 	} while (0)
 
 #undef __rel_bitmask

include/uapi/linux/user_events.h

@@ -12,6 +12,7 @@
 #include <linux/ioctl.h>
 
 #define USER_EVENTS_SYSTEM "user_events"
+#define USER_EVENTS_MULTI_SYSTEM "user_events_multi"
 #define USER_EVENTS_PREFIX "u:"
 
 /* Create dynamic location entry within a 32-bit value */
@@ -22,8 +23,11 @@ enum user_reg_flag {
 	/* Event will not delete upon last reference closing */
 	USER_EVENT_REG_PERSIST		= 1U << 0,
 
+	/* Event will be allowed to have multiple formats */
+	USER_EVENT_REG_MULTI_FORMAT	= 1U << 1,
+
 	/* This value or above is currently non-ABI */
-	USER_EVENT_REG_MAX		= 1U << 1,
+	USER_EVENT_REG_MAX		= 1U << 2,
 };
 
 /*

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",