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, 452 insertions, 0 deletions

diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
new file mode 100644
index 000000000..090ec60fb
--- /dev/null
+++ b/fs/ocfs2/acl.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * acl.c
+ *
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
+ *
+ * CREDITS:
+ * Lots of code in this file is copy from linux/fs/ext3/acl.c.
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/fs_struct.h>
+
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "alloc.h"
+#include "dlmglue.h"
+#include "file.h"
+#include "inode.h"
+#include "journal.h"
+#include "ocfs2_fs.h"
+
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from xattr value to acl struct.
+ */
+static struct posix_acl *ocfs2_acl_from_xattr(const void *value, size_t size)
+{
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(struct posix_acl_entry))
+		return ERR_PTR(-EINVAL);
+
+	count = size / sizeof(struct posix_acl_entry);
+
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n = 0; n < count; n++) {
+		struct ocfs2_acl_entry *entry =
+			(struct ocfs2_acl_entry *)value;
+
+		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+		switch(acl->a_entries[n].e_tag) {
+		case ACL_USER:
+			acl->a_entries[n].e_uid =
+				make_kuid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+		case ACL_GROUP:
+			acl->a_entries[n].e_gid =
+				make_kgid(&init_user_ns,
+					  le32_to_cpu(entry->e_id));
+			break;
+		default:
+			break;
+		}
+		value += sizeof(struct posix_acl_entry);
+
+	}
+	return acl;
+}
+
+/*
+ * Convert acl struct to xattr value.
+ */
+static void *ocfs2_acl_to_xattr(const struct posix_acl *acl, size_t *size)
+{
+	struct ocfs2_acl_entry *entry = NULL;
+	char *ocfs2_acl;
+	size_t n;
+
+	*size = acl->a_count * sizeof(struct posix_acl_entry);
+
+	ocfs2_acl = kmalloc(*size, GFP_NOFS);
+	if (!ocfs2_acl)
+		return ERR_PTR(-ENOMEM);
+
+	entry = (struct ocfs2_acl_entry *)ocfs2_acl;
+	for (n = 0; n < acl->a_count; n++, entry++) {
+		entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+		switch(acl->a_entries[n].e_tag) {
+		case ACL_USER:
+			entry->e_id = cpu_to_le32(
+				from_kuid(&init_user_ns,
+					  acl->a_entries[n].e_uid));
+			break;
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(
+				from_kgid(&init_user_ns,
+					  acl->a_entries[n].e_gid));
+			break;
+		default:
+			entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
+			break;
+		}
+	}
+	return ocfs2_acl;
+}
+
+static struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode, int type,
+					      struct buffer_head *di_bh)
+{
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	retval = ocfs2_xattr_get_nolock(inode, di_bh, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
+						"", value, retval);
+	}
+
+	if (retval > 0)
+		acl = ocfs2_acl_from_xattr(value, retval);
+	else if (retval == -ENODATA || retval == 0)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+
+	kfree(value);
+
+	return acl;
+}
+
+/*
+ * Helper function to set i_mode in memory and disk. Some call paths
+ * will not have di_bh or a journal handle to pass, in which case it
+ * will create it's own.
+ */
+static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
+			      handle_t *handle, umode_t new_mode)
+{
+	int ret, commit_handle = 0;
+	struct ocfs2_dinode *di;
+
+	if (di_bh == NULL) {
+		ret = ocfs2_read_inode_block(inode, &di_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	} else
+		get_bh(di_bh);
+
+	if (handle == NULL) {
+		handle = ocfs2_start_trans(OCFS2_SB(inode->i_sb),
+					   OCFS2_INODE_UPDATE_CREDITS);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			mlog_errno(ret);
+			goto out_brelse;
+		}
+
+		commit_handle = 1;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	inode->i_mode = new_mode;
+	inode_set_ctime_current(inode);
+	di->i_mode = cpu_to_le16(inode->i_mode);
+	di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode));
+	di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
+	ocfs2_update_inode_fsync_trans(handle, inode, 0);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+out_commit:
+	if (commit_handle)
+		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out_brelse:
+	brelse(di_bh);
+out:
+	return ret;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ */
+static int ocfs2_set_acl(handle_t *handle,
+			 struct inode *inode,
+			 struct buffer_head *di_bh,
+			 int type,
+			 struct posix_acl *acl,
+			 struct ocfs2_alloc_context *meta_ac,
+			 struct ocfs2_alloc_context *data_ac)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int ret;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (acl) {
+		value = ocfs2_acl_to_xattr(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	if (handle)
+		ret = ocfs2_xattr_set_handle(handle, inode, di_bh, name_index,
+					     "", value, size, 0,
+					     meta_ac, data_ac);
+	else
+		ret = ocfs2_xattr_set(inode, name_index, "", value, size, 0);
+
+	kfree(value);
+	if (!ret)
+		set_cached_acl(inode, type, acl);
+
+	return ret;
+}
+
+int ocfs2_iop_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		      struct posix_acl *acl, int type)
+{
+	struct buffer_head *bh = NULL;
+	int status, had_lock;
+	struct ocfs2_lock_holder oh;
+	struct inode *inode = d_inode(dentry);
+
+	had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh);
+	if (had_lock < 0)
+		return had_lock;
+	if (type == ACL_TYPE_ACCESS && acl) {
+		umode_t mode;
+
+		status = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode,
+					       &acl);
+		if (status)
+			goto unlock;
+
+		status = ocfs2_acl_set_mode(inode, bh, NULL, mode);
+		if (status)
+			goto unlock;
+	}
+	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
+unlock:
+	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
+	brelse(bh);
+	return status;
+}
+
+struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type, bool rcu)
+{
+	struct ocfs2_super *osb;
+	struct buffer_head *di_bh = NULL;
+	struct posix_acl *acl;
+	int had_lock;
+	struct ocfs2_lock_holder oh;
+
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	osb = OCFS2_SB(inode->i_sb);
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return NULL;
+
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh);
+	if (had_lock < 0)
+		return ERR_PTR(had_lock);
+
+	down_read(&OCFS2_I(inode)->ip_xattr_sem);
+	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
+	up_read(&OCFS2_I(inode)->ip_xattr_sem);
+
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
+	brelse(di_bh);
+	return acl;
+}
+
+int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl;
+	int ret;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return 0;
+
+	down_read(&OCFS2_I(inode)->ip_xattr_sem);
+	acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
+	up_read(&OCFS2_I(inode)->ip_xattr_sem);
+	if (IS_ERR_OR_NULL(acl))
+		return PTR_ERR_OR_ZERO(acl);
+	ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+	if (ret)
+		return ret;
+	ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
+			    acl, NULL, NULL);
+	posix_acl_release(acl);
+	return ret;
+}
+
+/*
+ * Initialize the ACLs of a new inode. If parent directory has default ACL,
+ * then clone to new inode. Called from ocfs2_mknod.
+ */
+void ocfs2_acl_init_release(struct ocfs2_acl_state *state)
+{
+	posix_acl_release(state->default_acl);
+	posix_acl_release(state->acl);
+	state->default_acl = NULL;
+	state->acl = NULL;
+}
+
+int ocfs2_acl_init_prepare(struct inode *inode, struct inode *dir,
+			   struct buffer_head *dir_bh,
+			   struct ocfs2_acl_state *state)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int ret = 0;
+
+	state->default_acl = NULL;
+	state->acl = NULL;
+	state->mode = inode->i_mode;
+
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
+	if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+		down_read(&OCFS2_I(dir)->ip_xattr_sem);
+		state->default_acl =
+			ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, dir_bh);
+		up_read(&OCFS2_I(dir)->ip_xattr_sem);
+		if (IS_ERR(state->default_acl)) {
+			ret = PTR_ERR(state->default_acl);
+			state->default_acl = NULL;
+			return ret;
+		}
+		if (state->default_acl) {
+			state->acl = posix_acl_dup(state->default_acl);
+			if (!state->acl) {
+				ret = -ENOMEM;
+				goto cleanup;
+			}
+			ret = __posix_acl_create(&state->acl, GFP_NOFS,
+						 &state->mode);
+			if (ret < 0)
+				goto cleanup;
+			if (ret == 0) {
+				posix_acl_release(state->acl);
+				state->acl = NULL;
+			}
+			if (!S_ISDIR(inode->i_mode)) {
+				posix_acl_release(state->default_acl);
+				state->default_acl = NULL;
+			}
+		} else {
+			state->mode &= ~current_umask();
+		}
+	} else {
+		state->mode &= ~current_umask();
+	}
+
+	return 0;
+cleanup:
+	ocfs2_acl_init_release(state);
+	return ret;
+}
+
+int ocfs2_init_acl(handle_t *handle, struct inode *inode,
+		   struct buffer_head *di_bh,
+		   struct ocfs2_alloc_context *meta_ac,
+		   struct ocfs2_alloc_context *data_ac,
+		   struct ocfs2_acl_state *state)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int ret = 0;
+
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
+	if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+		if (S_ISDIR(inode->i_mode) && state->default_acl) {
+			ret = ocfs2_set_acl(handle, inode, di_bh,
+					    ACL_TYPE_DEFAULT,
+					    state->default_acl, meta_ac,
+					    data_ac);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = ocfs2_acl_set_mode(inode, di_bh, handle, state->mode);
+	if (ret) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+		if (state->acl) {
+			ret = ocfs2_set_acl(handle, inode, di_bh,
+					    ACL_TYPE_ACCESS, state->acl,
+					    meta_ac, data_ac);
+		}
+	}
+
+	return ret;
+}