Merge tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "These are the latest RCU updates for v5.12:

   - Documentation updates.

   - Miscellaneous fixes.

   - kfree_rcu() updates: Addition of mem_dump_obj() to provide
     allocator return addresses to more easily locate bugs. This has a
     couple of RCU-related commits, but is mostly MM. Was pulled in with
     akpm's agreement.

   - Per-callback-batch tracking of numbers of callbacks, which enables
     better debugging information and smarter reactions to large numbers
     of callbacks.

   - The first round of changes to allow CPUs to be runtime switched
     from and to callback-offloaded state.

   - CONFIG_PREEMPT_RT-related changes.

   - RCU CPU stall warning updates.

   - Addition of polling grace-period APIs for SRCU.

   - Torture-test and torture-test scripting updates, including a
     "torture everything" script that runs rcutorture, locktorture,
     scftorture, rcuscale, and refscale. Plus does an allmodconfig
     build.

   - nolibc fixes for the torture tests"

* tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (130 commits)
  percpu_ref: Dump mem_dump_obj() info upon reference-count underflow
  rcu: Make call_rcu() print mem_dump_obj() info for double-freed callback
  mm: Make mem_obj_dump() vmalloc() dumps include start and length
  mm: Make mem_dump_obj() handle vmalloc() memory
  mm: Make mem_dump_obj() handle NULL and zero-sized pointers
  mm: Add mem_dump_obj() to print source of memory block
  tools/rcutorture: Fix position of -lgcc in mkinitrd.sh
  tools/nolibc: Fix position of -lgcc in the documented example
  tools/nolibc: Emit detailed error for missing alternate syscall number definitions
  tools/nolibc: Remove incorrect definitions of __ARCH_WANT_*
  tools/nolibc: Get timeval, timespec and timezone from linux/time.h
  tools/nolibc: Implement poll() based on ppoll()
  tools/nolibc: Implement fork() based on clone()
  tools/nolibc: Make getpgrp() fall back to getpgid(0)
  tools/nolibc: Make dup2() rely on dup3() when available
  tools/nolibc: Add the definition for dup()
  rcutorture: Add rcutree.use_softirq=0 to RUDE01 and TASKS01
  torture: Maintain torture-specific set of CPUs-online books
  torture: Clean up after torture-test CPU hotplugging
  rcutorture: Make object_debug also double call_rcu() heap object
  ...

7 files changed, 197 insertions, 0 deletions

diff --git a/mm/slab.c b/mm/slab.c
index d7c8da9319c7..dcc55e78f353 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3635,6 +3635,26 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
 EXPORT_SYMBOL(__kmalloc_node_track_caller);
 #endif /* CONFIG_NUMA */
 
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+{
+	struct kmem_cache *cachep;
+	unsigned int objnr;
+	void *objp;
+
+	kpp->kp_ptr = object;
+	kpp->kp_page = page;
+	cachep = page->slab_cache;
+	kpp->kp_slab_cache = cachep;
+	objp = object - obj_offset(cachep);
+	kpp->kp_data_offset = obj_offset(cachep);
+	page = virt_to_head_page(objp);
+	objnr = obj_to_index(cachep, page, objp);
+	objp = index_to_obj(cachep, page, objnr);
+	kpp->kp_objp = objp;
+	if (DEBUG && cachep->flags & SLAB_STORE_USER)
+		kpp->kp_ret = *dbg_userword(cachep, objp);
+}
+
 /**
  * __do_kmalloc - allocate memory
  * @size: how many bytes of memory are required.
diff --git a/mm/slab.h b/mm/slab.h
index 1a756a359fa8..ecad9b57bc44 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -615,4 +615,16 @@ static inline bool slab_want_init_on_free(struct kmem_cache *c)
 	return false;
 }
 
+#define KS_ADDRS_COUNT 16
+struct kmem_obj_info {
+	void *kp_ptr;
+	struct page *kp_page;
+	void *kp_objp;
+	unsigned long kp_data_offset;
+	struct kmem_cache *kp_slab_cache;
+	void *kp_ret;
+	void *kp_stack[KS_ADDRS_COUNT];
+};
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page);
+
 #endif /* MM_SLAB_H */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index e981c80d216c..adbace4256ef 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -537,6 +537,81 @@ bool slab_is_available(void)
 	return slab_state >= UP;
 }
 
+/**
+ * kmem_valid_obj - does the pointer reference a valid slab object?
+ * @object: pointer to query.
+ *
+ * Return: %true if the pointer is to a not-yet-freed object from
+ * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
+ * is to an already-freed object, and %false otherwise.
+ */
+bool kmem_valid_obj(void *object)
+{
+	struct page *page;
+
+	/* Some arches consider ZERO_SIZE_PTR to be a valid address. */
+	if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
+		return false;
+	page = virt_to_head_page(object);
+	return PageSlab(page);
+}
+
+/**
+ * kmem_dump_obj - Print available slab provenance information
+ * @object: slab object for which to find provenance information.
+ *
+ * This function uses pr_cont(), so that the caller is expected to have
+ * printed out whatever preamble is appropriate.  The provenance information
+ * depends on the type of object and on how much debugging is enabled.
+ * For a slab-cache object, the fact that it is a slab object is printed,
+ * and, if available, the slab name, return address, and stack trace from
+ * the allocation of that object.
+ *
+ * This function will splat if passed a pointer to a non-slab object.
+ * If you are not sure what type of object you have, you should instead
+ * use mem_dump_obj().
+ */
+void kmem_dump_obj(void *object)
+{
+	char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc";
+	int i;
+	struct page *page;
+	unsigned long ptroffset;
+	struct kmem_obj_info kp = { };
+
+	if (WARN_ON_ONCE(!virt_addr_valid(object)))
+		return;
+	page = virt_to_head_page(object);
+	if (WARN_ON_ONCE(!PageSlab(page))) {
+		pr_cont(" non-slab memory.\n");
+		return;
+	}
+	kmem_obj_info(&kp, object, page);
+	if (kp.kp_slab_cache)
+		pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name);
+	else
+		pr_cont(" slab%s", cp);
+	if (kp.kp_objp)
+		pr_cont(" start %px", kp.kp_objp);
+	if (kp.kp_data_offset)
+		pr_cont(" data offset %lu", kp.kp_data_offset);
+	if (kp.kp_objp) {
+		ptroffset = ((char *)object - (char *)kp.kp_objp) - kp.kp_data_offset;
+		pr_cont(" pointer offset %lu", ptroffset);
+	}
+	if (kp.kp_slab_cache && kp.kp_slab_cache->usersize)
+		pr_cont(" size %u", kp.kp_slab_cache->usersize);
+	if (kp.kp_ret)
+		pr_cont(" allocated at %pS\n", kp.kp_ret);
+	else
+		pr_cont("\n");
+	for (i = 0; i < ARRAY_SIZE(kp.kp_stack); i++) {
+		if (!kp.kp_stack[i])
+			break;
+		pr_info("    %pS\n", kp.kp_stack[i]);
+	}
+}
+
 #ifndef CONFIG_SLOB
 /* Create a cache during boot when no slab services are available yet */
 void __init create_boot_cache(struct kmem_cache *s, const char *name,
diff --git a/mm/slob.c b/mm/slob.c
index 8d4bfa46247f..ef87ada8705d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -461,6 +461,12 @@ out:
 	spin_unlock_irqrestore(&slob_lock, flags);
 }
 
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+{
+	kpp->kp_ptr = object;
+	kpp->kp_page = page;
+}
+
 /*
  * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
  */
diff --git a/mm/slub.c b/mm/slub.c
index b22a4b101c84..f5baf429654f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3933,6 +3933,46 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 	return 0;
 }
 
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+{
+	void *base;
+	int __maybe_unused i;
+	unsigned int objnr;
+	void *objp;
+	void *objp0;
+	struct kmem_cache *s = page->slab_cache;
+	struct track __maybe_unused *trackp;
+
+	kpp->kp_ptr = object;
+	kpp->kp_page = page;
+	kpp->kp_slab_cache = s;
+	base = page_address(page);
+	objp0 = kasan_reset_tag(object);
+#ifdef CONFIG_SLUB_DEBUG
+	objp = restore_red_left(s, objp0);
+#else
+	objp = objp0;
+#endif
+	objnr = obj_to_index(s, page, objp);
+	kpp->kp_data_offset = (unsigned long)((char *)objp0 - (char *)objp);
+	objp = base + s->size * objnr;
+	kpp->kp_objp = objp;
+	if (WARN_ON_ONCE(objp < base || objp >= base + page->objects * s->size || (objp - base) % s->size) ||
+	    !(s->flags & SLAB_STORE_USER))
+		return;
+#ifdef CONFIG_SLUB_DEBUG
+	trackp = get_track(s, objp, TRACK_ALLOC);
+	kpp->kp_ret = (void *)trackp->addr;
+#ifdef CONFIG_STACKTRACE
+	for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
+		kpp->kp_stack[i] = (void *)trackp->addrs[i];
+		if (!kpp->kp_stack[i])
+			break;
+	}
+#endif
+#endif
+}
+
 /********************************************************************
  *		Kmalloc subsystem
  *******************************************************************/
diff --git a/mm/util.c b/mm/util.c
index 8c9b7d1e7c49..54870226cea6 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -982,3 +982,34 @@ int __weak memcmp_pages(struct page *page1, struct page *page2)
 	kunmap_atomic(addr1);
 	return ret;
 }
+
+/**
+ * mem_dump_obj - Print available provenance information
+ * @object: object for which to find provenance information.
+ *
+ * This function uses pr_cont(), so that the caller is expected to have
+ * printed out whatever preamble is appropriate.  The provenance information
+ * depends on the type of object and on how much debugging is enabled.
+ * For example, for a slab-cache object, the slab name is printed, and,
+ * if available, the return address and stack trace from the allocation
+ * of that object.
+ */
+void mem_dump_obj(void *object)
+{
+	if (kmem_valid_obj(object)) {
+		kmem_dump_obj(object);
+		return;
+	}
+	if (vmalloc_dump_obj(object))
+		return;
+	if (!virt_addr_valid(object)) {
+		if (object == NULL)
+			pr_cont(" NULL pointer.\n");
+		else if (object == ZERO_SIZE_PTR)
+			pr_cont(" zero-size pointer.\n");
+		else
+			pr_cont(" non-paged memory.\n");
+		return;
+	}
+	pr_cont(" non-slab/vmalloc memory.\n");
+}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e6f352bf0498..4f5f8c907897 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3450,6 +3450,19 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 }
 #endif	/* CONFIG_SMP */
 
+bool vmalloc_dump_obj(void *object)
+{
+	struct vm_struct *vm;
+	void *objp = (void *)PAGE_ALIGN((unsigned long)object);
+
+	vm = find_vm_area(objp);
+	if (!vm)
+		return false;
+	pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
+		vm->nr_pages, (unsigned long)vm->addr, vm->caller);
+	return true;
+}
+
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)
 	__acquires(&vmap_purge_lock)