Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 387 insertions, 0 deletions

diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
new file mode 100644
index 000000000..fdb785fa4
--- /dev/null
+++ b/include/ras/ras_event.h
@@ -0,0 +1,387 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ras
+#define TRACE_INCLUDE_FILE ras_event
+
+#if !defined(_TRACE_HW_EVENT_MC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HW_EVENT_MC_H
+
+#include <linux/tracepoint.h>
+#include <linux/edac.h>
+#include <linux/ktime.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <linux/cper.h>
+
+/*
+ * MCE Extended Error Log trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event.
+ */
+
+/* memory trace event */
+
+#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)
+TRACE_EVENT(extlog_mem_event,
+	TP_PROTO(struct cper_sec_mem_err *mem,
+		 u32 err_seq,
+		 const guid_t *fru_id,
+		 const char *fru_text,
+		 u8 sev),
+
+	TP_ARGS(mem, err_seq, fru_id, fru_text, sev),
+
+	TP_STRUCT__entry(
+		__field(u32, err_seq)
+		__field(u8, etype)
+		__field(u8, sev)
+		__field(u64, pa)
+		__field(u8, pa_mask_lsb)
+		__field_struct(guid_t, fru_id)
+		__string(fru_text, fru_text)
+		__field_struct(struct cper_mem_err_compact, data)
+	),
+
+	TP_fast_assign(
+		__entry->err_seq = err_seq;
+		if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
+			__entry->etype = mem->error_type;
+		else
+			__entry->etype = ~0;
+		__entry->sev = sev;
+		if (mem->validation_bits & CPER_MEM_VALID_PA)
+			__entry->pa = mem->physical_addr;
+		else
+			__entry->pa = ~0ull;
+
+		if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
+			__entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask);
+		else
+			__entry->pa_mask_lsb = ~0;
+		__entry->fru_id = *fru_id;
+		__assign_str(fru_text);
+		cper_mem_err_pack(mem, &__entry->data);
+	),
+
+	TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %pUl %.20s",
+		  __entry->err_seq,
+		  cper_severity_str(__entry->sev),
+		  cper_mem_err_type_str(__entry->etype),
+		  __entry->pa,
+		  __entry->pa_mask_lsb,
+		  cper_mem_err_unpack(p, &__entry->data),
+		  &__entry->fru_id,
+		  __get_str(fru_text))
+);
+#endif
+
+/*
+ * Hardware Events Report
+ *
+ * Those events are generated when hardware detected a corrected or
+ * uncorrected event, and are meant to replace the current API to report
+ * errors defined on both EDAC and MCE subsystems.
+ *
+ * FIXME: Add events for handling memory errors originated from the
+ *        MCE subsystem.
+ */
+
+/*
+ * Hardware-independent Memory Controller specific events
+ */
+
+/*
+ * Default error mechanisms for Memory Controller errors (CE and UE)
+ */
+TRACE_EVENT(mc_event,
+
+	TP_PROTO(const unsigned int err_type,
+		 const char *error_msg,
+		 const char *label,
+		 const int error_count,
+		 const u8 mc_index,
+		 const s8 top_layer,
+		 const s8 mid_layer,
+		 const s8 low_layer,
+		 unsigned long address,
+		 const u8 grain_bits,
+		 unsigned long syndrome,
+		 const char *driver_detail),
+
+	TP_ARGS(err_type, error_msg, label, error_count, mc_index,
+		top_layer, mid_layer, low_layer, address, grain_bits,
+		syndrome, driver_detail),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	error_type		)
+		__string(	msg,		error_msg		)
+		__string(	label,		label			)
+		__field(	u16,		error_count		)
+		__field(	u8,		mc_index		)
+		__field(	s8,		top_layer		)
+		__field(	s8,		middle_layer		)
+		__field(	s8,		lower_layer		)
+		__field(	long,		address			)
+		__field(	u8,		grain_bits		)
+		__field(	long,		syndrome		)
+		__string(	driver_detail,	driver_detail		)
+	),
+
+	TP_fast_assign(
+		__entry->error_type		= err_type;
+		__assign_str(msg);
+		__assign_str(label);
+		__entry->error_count		= error_count;
+		__entry->mc_index		= mc_index;
+		__entry->top_layer		= top_layer;
+		__entry->middle_layer		= mid_layer;
+		__entry->lower_layer		= low_layer;
+		__entry->address		= address;
+		__entry->grain_bits		= grain_bits;
+		__entry->syndrome		= syndrome;
+		__assign_str(driver_detail);
+	),
+
+	TP_printk("%d %s error%s:%s%s on %s (mc:%d location:%d:%d:%d address:0x%08lx grain:%d syndrome:0x%08lx%s%s)",
+		  __entry->error_count,
+		  mc_event_error_type(__entry->error_type),
+		  __entry->error_count > 1 ? "s" : "",
+		  __get_str(msg)[0] ? " " : "",
+		  __get_str(msg),
+		  __get_str(label),
+		  __entry->mc_index,
+		  __entry->top_layer,
+		  __entry->middle_layer,
+		  __entry->lower_layer,
+		  __entry->address,
+		  1 << __entry->grain_bits,
+		  __entry->syndrome,
+		  __get_str(driver_detail)[0] ? " " : "",
+		  __get_str(driver_detail))
+);
+
+/*
+ * ARM Processor Events Report
+ *
+ * This event is generated when hardware detects an ARM processor error
+ * has occurred. UEFI 2.6 spec section N.2.4.4.
+ */
+#define APEIL "ARM Processor Err Info data len"
+#define APEID "ARM Processor Err Info raw data"
+#define APECIL "ARM Processor Err Context Info data len"
+#define APECID "ARM Processor Err Context Info raw data"
+#define VSEIL "Vendor Specific Err Info data len"
+#define VSEID "Vendor Specific Err Info raw data"
+TRACE_EVENT(arm_event,
+
+	TP_PROTO(const struct cper_sec_proc_arm *proc,
+		 const u8 *pei_err,
+		 const u32 pei_len,
+		 const u8 *ctx_err,
+		 const u32 ctx_len,
+		 const u8 *oem,
+		 const u32 oem_len,
+		 u8 sev,
+		 int cpu),
+
+	TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu),
+
+	TP_STRUCT__entry(
+		__field(u64, mpidr)
+		__field(u64, midr)
+		__field(u32, running_state)
+		__field(u32, psci_state)
+		__field(u8, affinity)
+		__field(u32, pei_len)
+		__dynamic_array(u8, pei_buf, pei_len)
+		__field(u32, ctx_len)
+		__dynamic_array(u8, ctx_buf, ctx_len)
+		__field(u32, oem_len)
+		__dynamic_array(u8, oem_buf, oem_len)
+		__field(u8, sev)
+		__field(int, cpu)
+	),
+
+	TP_fast_assign(
+		if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL)
+			__entry->affinity = proc->affinity_level;
+		else
+			__entry->affinity = ~0;
+		if (proc->validation_bits & CPER_ARM_VALID_MPIDR)
+			__entry->mpidr = proc->mpidr;
+		else
+			__entry->mpidr = 0ULL;
+		__entry->midr = proc->midr;
+		if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) {
+			__entry->running_state = proc->running_state;
+			__entry->psci_state = proc->psci_state;
+		} else {
+			__entry->running_state = ~0;
+			__entry->psci_state = ~0;
+		}
+		__entry->pei_len = pei_len;
+		memcpy(__get_dynamic_array(pei_buf), pei_err, pei_len);
+		__entry->ctx_len = ctx_len;
+		memcpy(__get_dynamic_array(ctx_buf), ctx_err, ctx_len);
+		__entry->oem_len = oem_len;
+		memcpy(__get_dynamic_array(oem_buf), oem, oem_len);
+		__entry->sev = sev;
+		__entry->cpu = cpu;
+	),
+
+	TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
+		  "running state: %d; PSCI state: %d; "
+		  "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s",
+		  __entry->cpu,
+		  __entry->sev,
+		  __entry->affinity, __entry->mpidr, __entry->midr,
+		  __entry->running_state, __entry->psci_state,
+		  APEIL, __entry->pei_len, APEID,
+		  __print_hex(__get_dynamic_array(pei_buf), __entry->pei_len),
+		  APECIL, __entry->ctx_len, APECID,
+		  __print_hex(__get_dynamic_array(ctx_buf), __entry->ctx_len),
+		  VSEIL, __entry->oem_len, VSEID,
+		  __print_hex(__get_dynamic_array(oem_buf), __entry->oem_len))
+);
+
+/*
+ * Non-Standard Section Report
+ *
+ * This event is generated when hardware detected a hardware
+ * error event, which may be of non-standard section as defined
+ * in UEFI spec appendix "Common Platform Error Record", or may
+ * be of sections for which TRACE_EVENT is not defined.
+ *
+ */
+TRACE_EVENT(non_standard_event,
+
+	TP_PROTO(const guid_t *sec_type,
+		 const guid_t *fru_id,
+		 const char *fru_text,
+		 const u8 sev,
+		 const u8 *err,
+		 const u32 len),
+
+	TP_ARGS(sec_type, fru_id, fru_text, sev, err, len),
+
+	TP_STRUCT__entry(
+		__array(char, sec_type, UUID_SIZE)
+		__array(char, fru_id, UUID_SIZE)
+		__string(fru_text, fru_text)
+		__field(u8, sev)
+		__field(u32, len)
+		__dynamic_array(u8, buf, len)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->sec_type, sec_type, UUID_SIZE);
+		memcpy(__entry->fru_id, fru_id, UUID_SIZE);
+		__assign_str(fru_text);
+		__entry->sev = sev;
+		__entry->len = len;
+		memcpy(__get_dynamic_array(buf), err, len);
+	),
+
+	TP_printk("severity: %d; sec type:%pU; FRU: %pU %s; data len:%d; raw data:%s",
+		  __entry->sev, __entry->sec_type,
+		  __entry->fru_id, __get_str(fru_text),
+		  __entry->len,
+		  __print_hex(__get_dynamic_array(buf), __entry->len))
+);
+
+#ifdef CONFIG_PCIEAER
+/*
+ * PCIe AER Trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event on a PCIe device. The event report has
+ * the following structure:
+ *
+ * char * dev_name -	The name of the slot where the device resides
+ *			([domain:]bus:device.function).
+ * u32 status -		Either the correctable or uncorrectable register
+ *			indicating what error or errors have been seen
+ * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
+ */
+
+#define aer_correctable_errors					\
+	{PCI_ERR_COR_RCVR,	"Receiver Error"},		\
+	{PCI_ERR_COR_BAD_TLP,	"Bad TLP"},			\
+	{PCI_ERR_COR_BAD_DLLP,	"Bad DLLP"},			\
+	{PCI_ERR_COR_REP_ROLL,	"RELAY_NUM Rollover"},		\
+	{PCI_ERR_COR_REP_TIMER,	"Replay Timer Timeout"},	\
+	{PCI_ERR_COR_ADV_NFAT,	"Advisory Non-Fatal Error"},	\
+	{PCI_ERR_COR_INTERNAL,	"Corrected Internal Error"},	\
+	{PCI_ERR_COR_LOG_OVER,	"Header Log Overflow"}
+
+#define aer_uncorrectable_errors				\
+	{PCI_ERR_UNC_UND,	"Undefined"},			\
+	{PCI_ERR_UNC_DLP,	"Data Link Protocol Error"},	\
+	{PCI_ERR_UNC_SURPDN,	"Surprise Down Error"},		\
+	{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"},		\
+	{PCI_ERR_UNC_FCP,	"Flow Control Protocol Error"},	\
+	{PCI_ERR_UNC_COMP_TIME,	"Completion Timeout"},		\
+	{PCI_ERR_UNC_COMP_ABORT,"Completer Abort"},		\
+	{PCI_ERR_UNC_UNX_COMP,	"Unexpected Completion"},	\
+	{PCI_ERR_UNC_RX_OVER,	"Receiver Overflow"},		\
+	{PCI_ERR_UNC_MALF_TLP,	"Malformed TLP"},		\
+	{PCI_ERR_UNC_ECRC,	"ECRC Error"},			\
+	{PCI_ERR_UNC_UNSUP,	"Unsupported Request Error"},	\
+	{PCI_ERR_UNC_ACSV,	"ACS Violation"},		\
+	{PCI_ERR_UNC_INTN,	"Uncorrectable Internal Error"},\
+	{PCI_ERR_UNC_MCBTLP,	"MC Blocked TLP"},		\
+	{PCI_ERR_UNC_ATOMEG,	"AtomicOp Egress Blocked"},	\
+	{PCI_ERR_UNC_TLPPRE,	"TLP Prefix Blocked Error"}
+
+TRACE_EVENT(aer_event,
+	TP_PROTO(const char *dev_name,
+		 const u32 status,
+		 const u8 severity,
+		 const u8 tlp_header_valid,
+		 struct pcie_tlp_log *tlp,
+		 const char *bus_type),
+
+
+	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp, bus_type),
+
+	TP_STRUCT__entry(
+		__string(	dev_name,	dev_name	)
+		__field(	u32,		status		)
+		__field(	u8,		severity	)
+		__field(	u8, 		tlp_header_valid)
+		__array(	u32, 		tlp_header, PCIE_STD_MAX_TLP_HEADERLOG)
+		__string(	bus_type,	bus_type	)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__assign_str(bus_type);
+		__entry->status		= status;
+		__entry->severity	= severity;
+		__entry->tlp_header_valid = tlp_header_valid;
+		if (tlp_header_valid) {
+			int i;
+
+			for (i = 0; i < PCIE_STD_MAX_TLP_HEADERLOG; i++)
+				__entry->tlp_header[i] = tlp->dw[i];
+		}
+	),
+
+	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
+		__get_str(dev_name), __get_str(bus_type),
+		__entry->severity == AER_CORRECTABLE ? "Corrected" :
+			__entry->severity == AER_FATAL ?
+			"Fatal" : "Uncorrected, non-fatal",
+		__entry->severity == AER_CORRECTABLE ?
+		__print_flags(__entry->status, "|", aer_correctable_errors) :
+		__print_flags(__entry->status, "|", aer_uncorrectable_errors),
+		__entry->tlp_header_valid ?
+			__print_array(__entry->tlp_header, PCIE_STD_MAX_TLP_HEADERLOG, 4) :
+			"Not available")
+);
+#endif /* CONFIG_PCIEAER */
+#endif /* _TRACE_HW_EVENT_MC_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>