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, 442 insertions, 0 deletions

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
new file mode 100644
index 000000000..b282e3a86
--- /dev/null
+++ b/include/trace/events/kvm.h
@@ -0,0 +1,442 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(_TRACE_KVM_MAIN_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_MAIN_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+#define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x }
+
+#define kvm_trace_exit_reason						\
+	ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL),	\
+	ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN),	\
+	ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR),	\
+	ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
+	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
+	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\
+	ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI),          \
+	ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR)
+
+TRACE_EVENT(kvm_userspace_exit,
+	    TP_PROTO(__u32 reason, int errno),
+	    TP_ARGS(reason, errno),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		reason		)
+		__field(	int,		errno		)
+	),
+
+	TP_fast_assign(
+		__entry->reason		= reason;
+		__entry->errno		= errno;
+	),
+
+	TP_printk("reason %s (%d)",
+		  __entry->errno < 0 ?
+		  (__entry->errno == -EINTR ? "restart" : "error") :
+		  __print_symbolic(__entry->reason, kvm_trace_exit_reason),
+		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
+);
+
+TRACE_EVENT(kvm_vcpu_wakeup,
+	    TP_PROTO(__u64 ns, bool waited, bool valid),
+	    TP_ARGS(ns, waited, valid),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		ns		)
+		__field(	bool,		waited		)
+		__field(	bool,		valid		)
+	),
+
+	TP_fast_assign(
+		__entry->ns		= ns;
+		__entry->waited		= waited;
+		__entry->valid		= valid;
+	),
+
+	TP_printk("%s time %lld ns, polling %s",
+		  __entry->waited ? "wait" : "poll",
+		  __entry->ns,
+		  __entry->valid ? "valid" : "invalid")
+);
+
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+TRACE_EVENT(kvm_set_irq,
+	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
+	TP_ARGS(gsi, level, irq_source_id),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	gsi		)
+		__field(	int,		level		)
+		__field(	int,		irq_source_id	)
+	),
+
+	TP_fast_assign(
+		__entry->gsi		= gsi;
+		__entry->level		= level;
+		__entry->irq_source_id	= irq_source_id;
+	),
+
+	TP_printk("gsi %u level %d source %d",
+		  __entry->gsi, __entry->level, __entry->irq_source_id)
+);
+
+#ifdef CONFIG_KVM_IOAPIC
+
+#define kvm_irqchips						\
+	{KVM_IRQCHIP_PIC_MASTER,	"PIC master"},		\
+	{KVM_IRQCHIP_PIC_SLAVE,		"PIC slave"},		\
+	{KVM_IRQCHIP_IOAPIC,		"IOAPIC"}
+
+#endif /* CONFIG_KVM_IOAPIC */
+
+#ifdef kvm_irqchips
+#define kvm_ack_irq_string "irqchip %s pin %u"
+#define kvm_ack_irq_parm  __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin
+#else
+#define kvm_ack_irq_string "irqchip %d pin %u"
+#define kvm_ack_irq_parm  __entry->irqchip, __entry->pin
+#endif
+
+TRACE_EVENT(kvm_ack_irq,
+	TP_PROTO(unsigned int irqchip, unsigned int pin),
+	TP_ARGS(irqchip, pin),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irqchip		)
+		__field(	unsigned int,	pin		)
+	),
+
+	TP_fast_assign(
+		__entry->irqchip	= irqchip;
+		__entry->pin		= pin;
+	),
+
+	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
+);
+
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
+
+
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+#define kvm_trace_symbol_mmio \
+	{ KVM_TRACE_MMIO_READ_UNSATISFIED, "unsatisfied-read" }, \
+	{ KVM_TRACE_MMIO_READ, "read" }, \
+	{ KVM_TRACE_MMIO_WRITE, "write" }
+
+TRACE_EVENT(kvm_mmio,
+	TP_PROTO(int type, int len, u64 gpa, void *val),
+	TP_ARGS(type, len, gpa, val),
+
+	TP_STRUCT__entry(
+		__field(	u32,	type		)
+		__field(	u32,	len		)
+		__field(	u64,	gpa		)
+		__field(	u64,	val		)
+	),
+
+	TP_fast_assign(
+		__entry->type		= type;
+		__entry->len		= len;
+		__entry->gpa		= gpa;
+		__entry->val		= 0;
+		if (val)
+			memcpy(&__entry->val, val,
+			       min_t(u32, sizeof(__entry->val), len));
+	),
+
+	TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx",
+		  __print_symbolic(__entry->type, kvm_trace_symbol_mmio),
+		  __entry->len, __entry->gpa, __entry->val)
+);
+
+#define kvm_fpu_load_symbol	\
+	{0, "unload"},		\
+	{1, "load"}
+
+TRACE_EVENT(kvm_fpu,
+	TP_PROTO(int load),
+	TP_ARGS(load),
+
+	TP_STRUCT__entry(
+		__field(	u32,	        load		)
+	),
+
+	TP_fast_assign(
+		__entry->load		= load;
+	),
+
+	TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol))
+);
+
+#ifdef CONFIG_KVM_ASYNC_PF
+DECLARE_EVENT_CLASS(kvm_async_get_page_class,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn),
+
+	TP_STRUCT__entry(
+		__field(__u64, gva)
+		__field(u64, gfn)
+	),
+
+	TP_fast_assign(
+		__entry->gva = gva;
+		__entry->gfn = gfn;
+	),
+
+	TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_repeated_fault,
+
+	TP_PROTO(u64 gva, u64 gfn),
+
+	TP_ARGS(gva, gfn)
+);
+
+DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva),
+
+	TP_STRUCT__entry(
+		__field(__u64, token)
+		__field(__u64, gva)
+	),
+
+	TP_fast_assign(
+		__entry->token = token;
+		__entry->gva = gva;
+	),
+
+	TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva)
+
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva)
+);
+
+DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready,
+
+	TP_PROTO(u64 token, u64 gva),
+
+	TP_ARGS(token, gva)
+);
+
+TRACE_EVENT(
+	kvm_async_pf_completed,
+	TP_PROTO(unsigned long address, u64 gva),
+	TP_ARGS(address, gva),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, address)
+		__field(u64, gva)
+		),
+
+	TP_fast_assign(
+		__entry->address = address;
+		__entry->gva = gva;
+		),
+
+	TP_printk("gva %#llx address %#lx",  __entry->gva,
+		  __entry->address)
+);
+
+#endif
+
+TRACE_EVENT(kvm_halt_poll_ns,
+	TP_PROTO(bool grow, unsigned int vcpu_id, unsigned int new,
+		 unsigned int old),
+	TP_ARGS(grow, vcpu_id, new, old),
+
+	TP_STRUCT__entry(
+		__field(bool, grow)
+		__field(unsigned int, vcpu_id)
+		__field(unsigned int, new)
+		__field(unsigned int, old)
+	),
+
+	TP_fast_assign(
+		__entry->grow           = grow;
+		__entry->vcpu_id        = vcpu_id;
+		__entry->new            = new;
+		__entry->old            = old;
+	),
+
+	TP_printk("vcpu %u: halt_poll_ns %u (%s %u)",
+			__entry->vcpu_id,
+			__entry->new,
+			__entry->grow ? "grow" : "shrink",
+			__entry->old)
+);
+
+#define trace_kvm_halt_poll_ns_grow(vcpu_id, new, old) \
+	trace_kvm_halt_poll_ns(true, vcpu_id, new, old)
+#define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \
+	trace_kvm_halt_poll_ns(false, vcpu_id, new, old)
+
+TRACE_EVENT(kvm_dirty_ring_push,
+	TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset),
+	TP_ARGS(ring, slot, offset),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+		__field(u32, slot)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+		__entry->slot           = slot;
+		__entry->offset         = offset;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x "
+		  "slot %u offset 0x%llx (used %u)",
+		  __entry->index, __entry->dirty_index,
+		  __entry->reset_index,  __entry->slot, __entry->offset,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_reset,
+	TP_PROTO(struct kvm_dirty_ring *ring),
+	TP_ARGS(ring),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)",
+		  __entry->index, __entry->dirty_index, __entry->reset_index,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_exit,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
+
+	TP_STRUCT__entry(
+	    __field(int, vcpu_id)
+	),
+
+	TP_fast_assign(
+	    __entry->vcpu_id = vcpu->vcpu_id;
+	),
+
+	TP_printk("vcpu %d", __entry->vcpu_id)
+);
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+/*
+ * @start:	Starting address of guest memory range
+ * @end:	End address of guest memory range
+ * @attr:	The value of the attribute being set.
+ */
+TRACE_EVENT(kvm_vm_set_mem_attributes,
+	TP_PROTO(gfn_t start, gfn_t end, unsigned long attr),
+	TP_ARGS(start, end, attr),
+
+	TP_STRUCT__entry(
+		__field(gfn_t,		start)
+		__field(gfn_t,		end)
+		__field(unsigned long,	attr)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+		__entry->attr		= attr;
+	),
+
+	TP_printk("%#016llx -- %#016llx [0x%lx]",
+		  __entry->start, __entry->end, __entry->attr)
+);
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+TRACE_EVENT(kvm_unmap_hva_range,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_age_hva,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
+);
+
+#endif /* _TRACE_KVM_MAIN_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>