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, 389 insertions, 0 deletions

diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
new file mode 100644
index 000000000..cb61fbdb5
--- /dev/null
+++ b/fs/mnt_idmapping.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */
+
+#include <linux/cred.h>
+#include <linux/fs.h>
+#include <linux/mnt_idmapping.h>
+#include <linux/slab.h>
+#include <linux/user_namespace.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+
+/*
+ * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t,
+ * never from raw values. These are just internal helpers.
+ */
+#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val }
+#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val }
+
+struct mnt_idmap {
+	struct uid_gid_map uid_map;
+	struct uid_gid_map gid_map;
+	refcount_t count;
+};
+
+/*
+ * Carries the initial idmapping of 0:0:4294967295 which is an identity
+ * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is
+ * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...].
+ */
+struct mnt_idmap nop_mnt_idmap = {
+	.count	= REFCOUNT_INIT(1),
+};
+EXPORT_SYMBOL_GPL(nop_mnt_idmap);
+
+/*
+ * Carries the invalid idmapping of a full 0-4294967295 {g,u}id range.
+ * This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID.
+ */
+struct mnt_idmap invalid_mnt_idmap = {
+	.count	= REFCOUNT_INIT(1),
+};
+EXPORT_SYMBOL_GPL(invalid_mnt_idmap);
+
+/**
+ * initial_idmapping - check whether this is the initial mapping
+ * @ns: idmapping to check
+ *
+ * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1,
+ * [...], 1000 to 1000 [...].
+ *
+ * Return: true if this is the initial mapping, false if not.
+ */
+static inline bool initial_idmapping(const struct user_namespace *ns)
+{
+	return ns == &init_user_ns;
+}
+
+/**
+ * make_vfsuid - map a filesystem kuid according to an idmapping
+ * @idmap: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @kuid : kuid to be mapped
+ *
+ * Take a @kuid and remap it from @fs_userns into @idmap. Use this
+ * function when preparing a @kuid to be reported to userspace.
+ *
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kuid unchanged.
+ * If initial_idmapping() tells us that the filesystem is not mounted with an
+ * idmapping we know the value of @kuid won't change when calling
+ * from_kuid() so we can simply retrieve the value via __kuid_val()
+ * directly.
+ *
+ * Return: @kuid mapped according to @idmap.
+ * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is
+ * returned.
+ */
+
+vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
+		     struct user_namespace *fs_userns,
+		     kuid_t kuid)
+{
+	uid_t uid;
+
+	if (idmap == &nop_mnt_idmap)
+		return VFSUIDT_INIT(kuid);
+	if (idmap == &invalid_mnt_idmap)
+		return INVALID_VFSUID;
+	if (initial_idmapping(fs_userns))
+		uid = __kuid_val(kuid);
+	else
+		uid = from_kuid(fs_userns, kuid);
+	if (uid == (uid_t)-1)
+		return INVALID_VFSUID;
+	return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid));
+}
+EXPORT_SYMBOL_GPL(make_vfsuid);
+
+/**
+ * make_vfsgid - map a filesystem kgid according to an idmapping
+ * @idmap: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @kgid : kgid to be mapped
+ *
+ * Take a @kgid and remap it from @fs_userns into @idmap. Use this
+ * function when preparing a @kgid to be reported to userspace.
+ *
+ * If initial_idmapping() determines that this is not an idmapped mount
+ * we can simply return @kgid unchanged.
+ * If initial_idmapping() tells us that the filesystem is not mounted with an
+ * idmapping we know the value of @kgid won't change when calling
+ * from_kgid() so we can simply retrieve the value via __kgid_val()
+ * directly.
+ *
+ * Return: @kgid mapped according to @idmap.
+ * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is
+ * returned.
+ */
+vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
+		     struct user_namespace *fs_userns, kgid_t kgid)
+{
+	gid_t gid;
+
+	if (idmap == &nop_mnt_idmap)
+		return VFSGIDT_INIT(kgid);
+	if (idmap == &invalid_mnt_idmap)
+		return INVALID_VFSGID;
+	if (initial_idmapping(fs_userns))
+		gid = __kgid_val(kgid);
+	else
+		gid = from_kgid(fs_userns, kgid);
+	if (gid == (gid_t)-1)
+		return INVALID_VFSGID;
+	return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid));
+}
+EXPORT_SYMBOL_GPL(make_vfsgid);
+
+/**
+ * from_vfsuid - map a vfsuid into the filesystem idmapping
+ * @idmap: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @vfsuid : vfsuid to be mapped
+ *
+ * Map @vfsuid into the filesystem idmapping. This function has to be used in
+ * order to e.g. write @vfsuid to inode->i_uid.
+ *
+ * Return: @vfsuid mapped into the filesystem idmapping
+ */
+kuid_t from_vfsuid(struct mnt_idmap *idmap,
+		   struct user_namespace *fs_userns, vfsuid_t vfsuid)
+{
+	uid_t uid;
+
+	if (idmap == &nop_mnt_idmap)
+		return AS_KUIDT(vfsuid);
+	if (idmap == &invalid_mnt_idmap)
+		return INVALID_UID;
+	uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid));
+	if (uid == (uid_t)-1)
+		return INVALID_UID;
+	if (initial_idmapping(fs_userns))
+		return KUIDT_INIT(uid);
+	return make_kuid(fs_userns, uid);
+}
+EXPORT_SYMBOL_GPL(from_vfsuid);
+
+/**
+ * from_vfsgid - map a vfsgid into the filesystem idmapping
+ * @idmap: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @vfsgid : vfsgid to be mapped
+ *
+ * Map @vfsgid into the filesystem idmapping. This function has to be used in
+ * order to e.g. write @vfsgid to inode->i_gid.
+ *
+ * Return: @vfsgid mapped into the filesystem idmapping
+ */
+kgid_t from_vfsgid(struct mnt_idmap *idmap,
+		   struct user_namespace *fs_userns, vfsgid_t vfsgid)
+{
+	gid_t gid;
+
+	if (idmap == &nop_mnt_idmap)
+		return AS_KGIDT(vfsgid);
+	if (idmap == &invalid_mnt_idmap)
+		return INVALID_GID;
+	gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid));
+	if (gid == (gid_t)-1)
+		return INVALID_GID;
+	if (initial_idmapping(fs_userns))
+		return KGIDT_INIT(gid);
+	return make_kgid(fs_userns, gid);
+}
+EXPORT_SYMBOL_GPL(from_vfsgid);
+
+#ifdef CONFIG_MULTIUSER
+/**
+ * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups
+ * @vfsgid: the mnt gid to match
+ *
+ * This function can be used to determine whether @vfsuid matches any of the
+ * caller's groups.
+ *
+ * Return: 1 if vfsuid matches caller's groups, 0 if not.
+ */
+int vfsgid_in_group_p(vfsgid_t vfsgid)
+{
+	return in_group_p(AS_KGIDT(vfsgid));
+}
+#else
+int vfsgid_in_group_p(vfsgid_t vfsgid)
+{
+	return 1;
+}
+#endif
+EXPORT_SYMBOL_GPL(vfsgid_in_group_p);
+
+static int copy_mnt_idmap(struct uid_gid_map *map_from,
+			  struct uid_gid_map *map_to)
+{
+	struct uid_gid_extent *forward, *reverse;
+	u32 nr_extents = READ_ONCE(map_from->nr_extents);
+	/* Pairs with smp_wmb() when writing the idmapping. */
+	smp_rmb();
+
+	/*
+	 * Don't blindly copy @map_to into @map_from if nr_extents is
+	 * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we
+	 * read @nr_extents someone could have written an idmapping and
+	 * then we might end up with inconsistent data. So just don't do
+	 * anything at all.
+	 */
+	if (nr_extents == 0)
+		return -EINVAL;
+
+	/*
+	 * Here we know that nr_extents is greater than zero which means
+	 * a map has been written. Since idmappings can't be changed
+	 * once they have been written we know that we can safely copy
+	 * from @map_to into @map_from.
+	 */
+
+	if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
+		*map_to = *map_from;
+		return 0;
+	}
+
+	forward = kmemdup_array(map_from->forward, nr_extents,
+				sizeof(struct uid_gid_extent),
+				GFP_KERNEL_ACCOUNT);
+	if (!forward)
+		return -ENOMEM;
+
+	reverse = kmemdup_array(map_from->reverse, nr_extents,
+				sizeof(struct uid_gid_extent),
+				GFP_KERNEL_ACCOUNT);
+	if (!reverse) {
+		kfree(forward);
+		return -ENOMEM;
+	}
+
+	/*
+	 * The idmapping isn't exposed anywhere so we don't need to care
+	 * about ordering between extent pointers and @nr_extents
+	 * initialization.
+	 */
+	map_to->forward = forward;
+	map_to->reverse = reverse;
+	map_to->nr_extents = nr_extents;
+	return 0;
+}
+
+static void free_mnt_idmap(struct mnt_idmap *idmap)
+{
+	if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->uid_map.forward);
+		kfree(idmap->uid_map.reverse);
+	}
+	if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->gid_map.forward);
+		kfree(idmap->gid_map.reverse);
+	}
+	kfree(idmap);
+}
+
+struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns)
+{
+	struct mnt_idmap *idmap;
+	int ret;
+
+	idmap = kzalloc_obj(struct mnt_idmap, GFP_KERNEL_ACCOUNT);
+	if (!idmap)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&idmap->count, 1);
+	ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map);
+	if (!ret)
+		ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map);
+	if (ret) {
+		free_mnt_idmap(idmap);
+		idmap = ERR_PTR(ret);
+	}
+	return idmap;
+}
+
+/**
+ * mnt_idmap_get - get a reference to an idmapping
+ * @idmap: the idmap to bump the reference on
+ *
+ * If @idmap is not the @nop_mnt_idmap bump the reference count.
+ *
+ * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed.
+ */
+struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap)
+{
+	if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap)
+		refcount_inc(&idmap->count);
+
+	return idmap;
+}
+EXPORT_SYMBOL_GPL(mnt_idmap_get);
+
+/**
+ * mnt_idmap_put - put a reference to an idmapping
+ * @idmap: the idmap to put the reference on
+ *
+ * If this is a non-initial idmapping, put the reference count when a mount is
+ * released and free it if we're the last user.
+ */
+void mnt_idmap_put(struct mnt_idmap *idmap)
+{
+	if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap &&
+	    refcount_dec_and_test(&idmap->count))
+		free_mnt_idmap(idmap);
+}
+EXPORT_SYMBOL_GPL(mnt_idmap_put);
+
+int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map)
+{
+	struct uid_gid_map *map, *map_up;
+	u32 idx, nr_mappings;
+
+	if (!is_valid_mnt_idmap(idmap))
+		return 0;
+
+	/*
+	 * Idmappings are shown relative to the caller's idmapping.
+	 * This is both the most intuitive and most useful solution.
+	 */
+	if (uid_map) {
+		map = &idmap->uid_map;
+		map_up = &current_user_ns()->uid_map;
+	} else {
+		map = &idmap->gid_map;
+		map_up = &current_user_ns()->gid_map;
+	}
+
+	for (idx = 0, nr_mappings = 0; idx < map->nr_extents; idx++) {
+		uid_t lower;
+		struct uid_gid_extent *extent;
+
+		if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+			extent = &map->extent[idx];
+		else
+			extent = &map->forward[idx];
+
+		/*
+		 * Verify that the whole range of the mapping can be
+		 * resolved in the caller's idmapping. If it cannot be
+		 * resolved skip the mapping.
+		 */
+		lower = map_id_range_up(map_up, extent->lower_first, extent->count);
+		if (lower == (uid_t) -1)
+			continue;
+
+		seq_printf(seq, "%u %u %u", extent->first, lower, extent->count);
+		if (seq_has_overflowed(seq))
+			return -EAGAIN;
+
+		seq->count++; /* mappings are separated by \0 */
+		if (seq_has_overflowed(seq))
+			return -EAGAIN;
+
+		nr_mappings++;
+	}
+
+	return nr_mappings;
+}