Merge tag 'probes-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull probes updates from Masami Hiramatsu:

 - tracing/probes: Add new pseudo-types %pd and %pD support for dumping
   dentry name from 'struct dentry *' and file name from 'struct file *'

 - uprobes performance optimizations:
    - Speed up the BPF uprobe event by delaying the fetching of the
      uprobe event arguments that are not used in BPF
    - Avoid locking by speculatively checking whether uprobe event is
      valid
    - Reduce lock contention by using read/write_lock instead of
      spinlock for uprobe list operation. This improved BPF uprobe
      benchmark result 43% on average

 - rethook: Remove non-fatal warning messages when tracing stack from
   BPF and skip rcu_is_watching() validation in rethook if possible

 - objpool: Optimize objpool (which is used by kretprobes and fprobe as
   rethook backend storage) by inlining functions and avoid caching
   nr_cpu_ids because it is a const value

 - fprobe: Add entry/exit callbacks types (code cleanup)

 - kprobes: Check ftrace was killed in kprobes if it uses ftrace

* tag 'probes-v6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  kprobe/ftrace: bail out if ftrace was killed
  selftests/ftrace: Fix required features for VFS type test case
  objpool: cache nr_possible_cpus() and avoid caching nr_cpu_ids
  objpool: enable inlining objpool_push() and objpool_pop() operations
  rethook: honor CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING in rethook_try_get()
  ftrace: make extra rcu_is_watching() validation check optional
  uprobes: reduce contention on uprobes_tree access
  rethook: Remove warning messages printed for finding return address of a frame.
  fprobe: Add entry/exit callbacks types
  selftests/ftrace: add fprobe test cases for VFS type "%pd" and "%pD"
  selftests/ftrace: add kprobe test cases for VFS type "%pd" and "%pD"
  Documentation: tracing: add new type '%pd' and '%pD' for kprobe
  tracing/probes: support '%pD' type for print struct file's name
  tracing/probes: support '%pd' type for print struct dentry's name
  uprobes: add speculative lockless system-wide uprobe filter check
  uprobes: prepare uprobe args buffer lazily
  uprobes: encapsulate preparation of uprobe args buffer

4 files changed, 121 insertions, 11 deletions

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 3e03758151f4..f39869588117 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -7,6 +7,16 @@
 #include <linux/ftrace.h>
 #include <linux/rethook.h>
 
+struct fprobe;
+
+typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip,
+			       unsigned long ret_ip, struct pt_regs *regs,
+			       void *entry_data);
+
+typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip,
+			       unsigned long ret_ip, struct pt_regs *regs,
+			       void *entry_data);
+
 /**
  * struct fprobe - ftrace based probe.
  * @ops: The ftrace_ops.
@@ -34,12 +44,8 @@ struct fprobe {
 	size_t			entry_data_size;
 	int			nr_maxactive;
 
-	int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
-			     void *entry_data);
-	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
-			     void *entry_data);
+	fprobe_entry_cb entry_handler;
+	fprobe_exit_cb  exit_handler;
 };
 
 /* This fprobe is soft-disabled. */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 0ff44d6633e3..5fcbc254d186 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -378,11 +378,15 @@ static inline void wait_for_kprobe_optimizer(void) { }
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct ftrace_regs *fregs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
+/* Set when ftrace has been killed: kprobes on ftrace must be disabled for safety */
+extern bool kprobe_ftrace_disabled __read_mostly;
+extern void kprobe_ftrace_kill(void);
 #else
 static inline int arch_prepare_kprobe_ftrace(struct kprobe *p)
 {
 	return -EINVAL;
 }
+static inline void kprobe_ftrace_kill(void) {}
 #endif /* CONFIG_KPROBES_ON_FTRACE */
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
@@ -495,6 +499,9 @@ static inline void kprobe_flush_task(struct task_struct *tk)
 static inline void kprobe_free_init_mem(void)
 {
 }
+static inline void kprobe_ftrace_kill(void)
+{
+}
 static inline int disable_kprobe(struct kprobe *kp)
 {
 	return -EOPNOTSUPP;
diff --git a/include/linux/objpool.h b/include/linux/objpool.h
index 15aff4a17f0c..cb1758eaa2d3 100644
--- a/include/linux/objpool.h
+++ b/include/linux/objpool.h
@@ -5,6 +5,10 @@
 
 #include <linux/types.h>
 #include <linux/refcount.h>
+#include <linux/atomic.h>
+#include <linux/cpumask.h>
+#include <linux/irqflags.h>
+#include <linux/smp.h>
 
 /*
  * objpool: ring-array based lockless MPMC queue
@@ -69,7 +73,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context);
  * struct objpool_head - object pooling metadata
  * @obj_size:   object size, aligned to sizeof(void *)
  * @nr_objs:    total objs (to be pre-allocated with objpool)
- * @nr_cpus:    local copy of nr_cpu_ids
+ * @nr_possible_cpus: cached value of num_possible_cpus()
  * @capacity:   max objs can be managed by one objpool_slot
  * @gfp:        gfp flags for kmalloc & vmalloc
  * @ref:        refcount of objpool
@@ -81,7 +85,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context);
 struct objpool_head {
 	int                     obj_size;
 	int                     nr_objs;
-	int                     nr_cpus;
+	int                     nr_possible_cpus;
 	int                     capacity;
 	gfp_t                   gfp;
 	refcount_t              ref;
@@ -118,13 +122,94 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
 		 gfp_t gfp, void *context, objpool_init_obj_cb objinit,
 		 objpool_fini_cb release);
 
+/* try to retrieve object from slot */
+static inline void *__objpool_try_get_slot(struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	/* load head snapshot, other cpus may change it */
+	uint32_t head = smp_load_acquire(&slot->head);
+
+	while (head != READ_ONCE(slot->last)) {
+		void *obj;
+
+		/*
+		 * data visibility of 'last' and 'head' could be out of
+		 * order since memory updating of 'last' and 'head' are
+		 * performed in push() and pop() independently
+		 *
+		 * before any retrieving attempts, pop() must guarantee
+		 * 'last' is behind 'head', that is to say, there must
+		 * be available objects in slot, which could be ensured
+		 * by condition 'last != head && last - head <= nr_objs'
+		 * that is equivalent to 'last - head - 1 < nr_objs' as
+		 * 'last' and 'head' are both unsigned int32
+		 */
+		if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) {
+			head = READ_ONCE(slot->head);
+			continue;
+		}
+
+		/* obj must be retrieved before moving forward head */
+		obj = READ_ONCE(slot->entries[head & slot->mask]);
+
+		/* move head forward to mark it's consumption */
+		if (try_cmpxchg_release(&slot->head, &head, head + 1))
+			return obj;
+	}
+
+	return NULL;
+}
+
 /**
  * objpool_pop() - allocate an object from objpool
  * @pool: object pool
  *
  * return value: object ptr or NULL if failed
  */
-void *objpool_pop(struct objpool_head *pool);
+static inline void *objpool_pop(struct objpool_head *pool)
+{
+	void *obj = NULL;
+	unsigned long flags;
+	int i, cpu;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+
+	cpu = raw_smp_processor_id();
+	for (i = 0; i < pool->nr_possible_cpus; i++) {
+		obj = __objpool_try_get_slot(pool, cpu);
+		if (obj)
+			break;
+		cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1);
+	}
+	raw_local_irq_restore(flags);
+
+	return obj;
+}
+
+/* adding object to slot, abort if the slot was already full */
+static inline int
+__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	uint32_t head, tail;
+
+	/* loading tail and head as a local snapshot, tail first */
+	tail = READ_ONCE(slot->tail);
+
+	do {
+		head = READ_ONCE(slot->head);
+		/* fault caught: something must be wrong */
+		WARN_ON_ONCE(tail - head > pool->nr_objs);
+	} while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1));
+
+	/* now the tail position is reserved for the given obj */
+	WRITE_ONCE(slot->entries[tail & slot->mask], obj);
+	/* update sequence to make this obj available for pop() */
+	smp_store_release(&slot->last, tail + 1);
+
+	return 0;
+}
 
 /**
  * objpool_push() - reclaim the object and return back to objpool
@@ -134,7 +219,19 @@ void *objpool_pop(struct objpool_head *pool);
  * return: 0 or error code (it fails only when user tries to push
  * the same object multiple times or wrong "objects" into objpool)
  */
-int objpool_push(void *obj, struct objpool_head *pool);
+static inline int objpool_push(void *obj, struct objpool_head *pool)
+{
+	unsigned long flags;
+	int rc;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+	rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id());
+	raw_local_irq_restore(flags);
+
+	return rc;
+}
+
 
 /**
  * objpool_drop() - discard the object and deref objpool
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index d48cd92d2364..24ea8ac049b4 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -135,7 +135,7 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
 # define do_ftrace_record_recursion(ip, pip)	do { } while (0)
 #endif
 
-#ifdef CONFIG_ARCH_WANTS_NO_INSTR
+#ifdef CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING
 # define trace_warn_on_no_rcu(ip)					\
 	({								\
 		bool __ret = !rcu_is_watching();			\