mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Nick Piggin <npiggin@kernel.dk>
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 40/46] fs: provide rcu-walk aware permission i_ops
Date: Sat, 27 Nov 2010 20:45:10 +1100	[thread overview]
Message-ID: <8cbc64c4c8ab6be0ae5a7fa00ebabc7a8d60641a.1290852960.git.npiggin@kernel.dk> (raw)
In-Reply-To: <cover.1290852958.git.npiggin@kernel.dk>

Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
 fs/namei.c         |  131 ++++++++++++++++++++++++++++++++++++++++------------
 include/linux/fs.h |    6 ++
 2 files changed, 107 insertions(+), 30 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index d8f7ece..7fa6119 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -169,8 +169,36 @@ EXPORT_SYMBOL(putname);
 /*
  * This does basic POSIX ACL permission checking
  */
-static inline int __acl_permission_check(struct inode *inode, int mask,
-		int (*check_acl)(struct inode *inode, int mask), int rcu)
+static int acl_permission_check_rcu(struct inode *inode, int mask, unsigned int flags,
+		int (*check_acl_rcu)(struct inode *inode, int mask, unsigned int flags))
+{
+	umode_t			mode = inode->i_mode;
+
+	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
+
+	if (current_fsuid() == inode->i_uid)
+		mode >>= 6;
+	else {
+		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl_rcu) {
+			int error = check_acl_rcu(inode, mask, flags);
+			if (error != -EAGAIN)
+				return error;
+		}
+
+		if (in_group_p(inode->i_gid))
+			mode >>= 3;
+	}
+
+	/*
+	 * If the DACs are ok we don't need any capability check.
+	 */
+	if ((mask & ~mode) == 0)
+		return 0;
+	return -EACCES;
+}
+
+static int acl_permission_check(struct inode *inode, int mask, unsigned int flags,
+		int (*check_acl)(struct inode *inode, int mask))
 {
 	umode_t			mode = inode->i_mode;
 
@@ -180,7 +208,7 @@ static inline int __acl_permission_check(struct inode *inode, int mask,
 		mode >>= 6;
 	else {
 		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
-			if (rcu) {
+			if (flags) {
 				return -ECHILD;
 			} else {
 				int error = check_acl(inode, mask);
@@ -201,10 +229,52 @@ static inline int __acl_permission_check(struct inode *inode, int mask,
 	return -EACCES;
 }
 
-static inline int acl_permission_check(struct inode *inode, int mask,
-		int (*check_acl)(struct inode *inode, int mask))
+/**
+ * generic_permission_rcu  -  check for access rights on a Posix-like filesystem
+ * @inode:	inode to check access rights for
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @check_acl_rcu: optional callback to check for Posix ACLs
+ * @flags	IPERM_FLAG_ flags.
+ *
+ * Used to check for read/write/execute permissions on a file.
+ * We use "fsuid" for this, letting us set arbitrary permissions
+ * for filesystem access without changing the "normal" uids which
+ * are used for other things.
+ *
+ * generic_permission_rcu must be rcu-walk aware. It should return
+ * -ECHILD in case an rcu-walk request cannot be satisfied (eg.
+ * requires blocking or too much thought!). It would then be called
+ * again in ref-walk mode.
+ */
+int generic_permission_rcu(struct inode *inode, int mask, unsigned int flags,
+	int (*check_acl_rcu)(struct inode *inode, int mask, unsigned int flags))
 {
-	return __acl_permission_check(inode, mask, check_acl, 0);
+	int ret;
+
+	/*
+	 * Do the basic POSIX ACL permission checks.
+	 */
+	ret = acl_permission_check_rcu(inode, mask, flags, check_acl_rcu);
+	if (ret != -EACCES)
+		return ret;
+
+	/*
+	 * Read/write DACs are always overridable.
+	 * Executable DACs are overridable if at least one exec bit is set.
+	 */
+	if (!(mask & MAY_EXEC) || execute_ok(inode))
+		if (capable(CAP_DAC_OVERRIDE))
+			return 0;
+
+	/*
+	 * Searching includes executable on directories, else just read.
+	 */
+	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
+	if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
+		if (capable(CAP_DAC_READ_SEARCH))
+			return 0;
+
+	return -EACCES;
 }
 
 /**
@@ -226,7 +296,7 @@ int generic_permission(struct inode *inode, int mask,
 	/*
 	 * Do the basic POSIX ACL permission checks.
 	 */
-	ret = acl_permission_check(inode, mask, check_acl);
+	ret = acl_permission_check(inode, mask, 0, check_acl);
 	if (ret != -EACCES)
 		return ret;
 
@@ -282,8 +352,14 @@ int inode_permission(struct inode *inode, int mask)
 
 	if (inode->i_op->permission)
 		retval = inode->i_op->permission(inode, mask);
+	else if (inode->i_op->permission_rcu)
+		retval = inode->i_op->permission_rcu(inode, mask, 0);
+	else if (inode->i_op->check_acl_rcu)
+		retval = generic_permission_rcu(inode, mask, 0,
+				inode->i_op->check_acl_rcu);
 	else
-		retval = generic_permission(inode, mask, inode->i_op->check_acl);
+		retval = generic_permission(inode, mask,
+				inode->i_op->check_acl);
 
 	if (retval)
 		return retval;
@@ -622,22 +698,26 @@ force_reval_path(struct path *path, struct nameidata *nd)
  * short-cut DAC fails, then call ->permission() to do more
  * complete permission check.
  */
-static inline int __exec_permission(struct inode *inode, int rcu)
+static inline int exec_permission(struct inode *inode, unsigned int flags)
 {
 	int ret;
 
-	if (inode->i_op->permission) {
-		if (rcu)
+	if (inode->i_op->permission_rcu) {
+		ret = inode->i_op->permission_rcu(inode, MAY_EXEC, flags);
+	} else if (inode->i_op->permission) {
+		if (flags)
 			return -ECHILD;
 		ret = inode->i_op->permission(inode, MAY_EXEC);
-		if (!ret)
-			goto ok;
-		return ret;
+	} else if (inode->i_op->check_acl_rcu) {
+		ret = acl_permission_check_rcu(inode, MAY_EXEC, flags,
+				inode->i_op->check_acl_rcu);
+	} else {
+		ret = acl_permission_check(inode, MAY_EXEC, flags,
+				inode->i_op->check_acl);
 	}
-	ret = __acl_permission_check(inode, MAY_EXEC, inode->i_op->check_acl, rcu);
-	if (!ret)
+	if (likely(!ret))
 		goto ok;
-	if (rcu && ret == -ECHILD)
+	if (ret == -ECHILD)
 		return ret;
 
 	if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH))
@@ -648,16 +728,6 @@ ok:
 	return security_inode_permission(inode, MAY_EXEC); /* XXX: ok for RCU? */
 }
 
-static int exec_permission(struct inode *inode)
-{
-	return __exec_permission(inode, 0);
-}
-
-static int exec_permission_rcu(struct inode *inode)
-{
-	return __exec_permission(inode, 1);
-}
-
 static __always_inline void set_root(struct nameidata *nd)
 {
 	if (!nd->root.mnt)
@@ -1126,7 +1196,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 
 		nd->flags |= LOOKUP_CONTINUE;
 		if (nd->flags & LOOKUP_RCU) {
-			err = exec_permission_rcu(nd->inode);
+			err = exec_permission(nd->inode, IPERM_FLAG_RCU);
 			if (err == -ECHILD) {
 				if (nameidata_drop_rcu(nd))
 					return -ECHILD;
@@ -1134,7 +1204,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			}
 		} else {
 exec_again:
-			err = exec_permission(nd->inode);
+			err = exec_permission(nd->inode, 0);
 		}
  		if (err)
 			break;
@@ -1567,7 +1637,7 @@ static struct dentry *__lookup_hash(struct qstr *name,
 	struct dentry *dentry;
 	int err;
 
-	err = exec_permission(inode);
+	err = exec_permission(inode, 0);
 	if (err)
 		return ERR_PTR(err);
 
@@ -3352,6 +3422,7 @@ EXPORT_SYMBOL(vfs_follow_link);
 EXPORT_SYMBOL(vfs_link);
 EXPORT_SYMBOL(vfs_mkdir);
 EXPORT_SYMBOL(vfs_mknod);
+EXPORT_SYMBOL(generic_permission_rcu);
 EXPORT_SYMBOL(generic_permission);
 EXPORT_SYMBOL(vfs_readlink);
 EXPORT_SYMBOL(vfs_rename);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 07e8a50..490eedd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1549,11 +1549,15 @@ struct file_operations {
 	int (*setlease)(struct file *, long, struct file_lock **);
 };
 
+#define IPERM_FLAG_RCU	0x0001
+
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	int (*permission) (struct inode *, int);
+	int (*permission_rcu) (struct inode *, int, unsigned int);
 	int (*check_acl)(struct inode *, int);
+	int (*check_acl_rcu)(struct inode *, int, unsigned int);
 
 	int (*readlink) (struct dentry *, char __user *,int);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -2164,6 +2168,8 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int inode_permission(struct inode *, int);
+extern int generic_permission_rcu(struct inode *, int, unsigned int,
+		int (*check_acl_rcu)(struct inode *, int, unsigned int));
 extern int generic_permission(struct inode *, int,
 		int (*check_acl)(struct inode *, int));
 
-- 
1.7.1


  parent reply	other threads:[~2010-11-27 10:31 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-27 10:15 [PATCH 00/46] rcu-walk and dcache scaling Nick Piggin
2010-11-27  9:44 ` [PATCH 02/46] fs: d_validate fixes Nick Piggin
2010-12-08  1:53   ` Dave Chinner
2010-12-08  6:59     ` Nick Piggin
2010-12-09  0:50       ` Dave Chinner
2010-12-09  4:50         ` Nick Piggin
2010-11-27  9:44 ` [PATCH 03/46] kernel: kmem_ptr_validate considered harmful Nick Piggin
2010-11-27  9:44 ` [PATCH 04/46] fs: dcache documentation cleanup Nick Piggin
2010-11-27  9:44 ` [PATCH 05/46] fs: change d_delete semantics Nick Piggin
2010-11-27  9:44 ` [PATCH 06/46] cifs: dont overwrite dentry name in d_revalidate Nick Piggin
2010-11-27  9:44 ` [PATCH 07/46] jfs: " Nick Piggin
2010-11-27  9:44 ` [PATCH 08/46] fs: change d_compare for rcu-walk Nick Piggin
2010-11-27  9:44 ` [PATCH 09/46] fs: change d_hash " Nick Piggin
2010-11-27  9:44 ` [PATCH 10/46] hostfs: simplify locking Nick Piggin
2010-11-27  9:44 ` [PATCH 11/46] fs: dcache scale hash Nick Piggin
2010-12-09  6:09   ` Dave Chinner
2010-12-09  6:28     ` Nick Piggin
2010-12-09  8:17       ` Dave Chinner
2010-12-09 12:53         ` Nick Piggin
2010-12-09 23:42           ` Dave Chinner
2010-12-10  2:35             ` Nick Piggin
2010-12-10  9:01               ` Dave Chinner
2010-12-13  4:48                 ` Nick Piggin
2010-12-13  5:05                 ` Nick Piggin
2010-11-27  9:44 ` [PATCH 12/46] fs: dcache scale lru Nick Piggin
2010-12-09  7:22   ` Dave Chinner
2010-12-09 12:34     ` Nick Piggin
2010-11-27  9:44 ` [PATCH 13/46] fs: dcache scale dentry refcount Nick Piggin
2010-11-27  9:44 ` [PATCH 14/46] fs: dcache scale d_unhashed Nick Piggin
2010-11-27  9:44 ` [PATCH 15/46] fs: dcache scale subdirs Nick Piggin
2010-11-27  9:44 ` [PATCH 16/46] fs: scale inode alias list Nick Piggin
2010-11-27  9:44 ` [PATCH 17/46] fs: Use rename lock and RCU for multi-step operations Nick Piggin
2011-01-18 22:32   ` Yehuda Sadeh Weinraub
2011-01-18 22:42     ` Nick Piggin
2011-01-19 22:27       ` Yehuda Sadeh Weinraub
2011-01-19 22:32         ` Nick Piggin
2011-01-25 22:10           ` Yehuda Sadeh Weinraub
2011-01-27  5:18             ` Nick Piggin
2011-02-07 18:52               ` Jim Schutt
2011-02-07 21:04                 ` Yehuda Sadeh Weinraub
2011-02-07 21:31                   ` Jim Schutt
2011-02-07 22:25                   ` Jim Schutt
2011-02-14 17:57               ` Yehuda Sadeh Weinraub
2010-11-27  9:44 ` [PATCH 18/46] fs: increase d_name lock coverage Nick Piggin
2010-11-27  9:44 ` [PATCH 19/46] fs: dcache remove dcache_lock Nick Piggin
2010-11-27  9:44 ` [PATCH 20/46] fs: dcache avoid starvation in dcache multi-step operations Nick Piggin
2010-11-27  9:44 ` [PATCH 21/46] fs: dcache reduce dput locking Nick Piggin
2010-11-27  9:44 ` [PATCH 22/46] fs: dcache reduce locking in d_alloc Nick Piggin
2010-11-27  9:44 ` [PATCH 23/46] fs: dcache reduce dcache_inode_lock Nick Piggin
2010-11-27  9:44 ` [PATCH 24/46] fs: dcache rationalise dget variants Nick Piggin
2010-11-27  9:44 ` [PATCH 25/46] fs: dcache reduce d_parent locking Nick Piggin
2010-11-27  9:44 ` [PATCH 26/46] fs: dcache reduce prune_one_dentry locking Nick Piggin
2010-11-27  9:44 ` [PATCH 27/46] fs: reduce dcache_inode_lock width in lru scanning Nick Piggin
2010-11-27  9:44 ` [PATCH 28/46] fs: use RCU in shrink_dentry_list to reduce lock nesting Nick Piggin
2010-11-27  9:44 ` [PATCH 29/46] fs: consolidate dentry kill sequence Nick Piggin
2010-11-27  9:45 ` [PATCH 30/46] fs: icache RCU free inodes Nick Piggin
2010-11-27  9:45 ` [PATCH 31/46] fs: avoid inode RCU freeing for pseudo fs Nick Piggin
2010-11-27  9:45 ` [PATCH 32/46] kernel: optimise seqlock Nick Piggin
2010-11-27  9:45 ` [PATCH 33/46] fs: rcu-walk for path lookup Nick Piggin
2010-11-27  9:45 ` [PATCH 34/46] fs: fs_struct use seqlock Nick Piggin
2010-11-27  9:45 ` [PATCH 35/46] fs: dcache remove d_mounted Nick Piggin
2010-11-27  9:45 ` [PATCH 36/46] fs: dcache reduce branches in lookup path Nick Piggin
2010-11-27  9:45 ` [PATCH 37/46] fs: cache optimise dentry and inode for rcu-walk Nick Piggin
2010-11-27  9:45 ` [PATCH 38/46] fs: prefetch inode data in dcache lookup Nick Piggin
2010-11-27  9:45 ` [PATCH 39/46] fs: d_revalidate_rcu for rcu-walk Nick Piggin
2010-11-27  9:45 ` Nick Piggin [this message]
2010-11-27  9:45 ` [PATCH 41/46] fs: provide simple rcu-walk ACL implementation Nick Piggin
2010-11-27  9:45 ` [PATCH 42/46] kernel: add bl_list Nick Piggin
2010-11-27  9:45 ` [PATCH 43/46] bit_spinlock: add required includes Nick Piggin
2010-11-27  9:45 ` [PATCH 44/46] fs: dcache per-bucket dcache hash locking Nick Piggin
2010-11-27  9:45 ` [PATCH 45/46] fs: dcache per-inode inode alias locking Nick Piggin
2010-11-27  9:45 ` [PATCH 46/46] fs: improve scalability of pseudo filesystems Nick Piggin
2010-11-27  9:56 ` [PATCH 01/46] Revert "fs: use RCU read side protection in d_validate" Nick Piggin
2010-12-08  1:16   ` Dave Chinner
2010-12-08  9:38     ` Nick Piggin
2010-12-09  0:44       ` Dave Chinner
2010-12-09  4:38         ` Nick Piggin
2010-12-09  5:16           ` Nick Piggin
2010-11-27 15:04 ` [PATCH 00/46] rcu-walk and dcache scaling Anca Emanuel
2010-11-28  3:28   ` Nick Piggin
2010-11-28  6:24     ` Sedat Dilek
2010-12-01 18:03 ` David Miller
2010-12-03 16:55   ` Nick Piggin
2010-12-07 11:25 ` Dave Chinner
2010-12-07 15:24   ` Nick Piggin
2010-12-07 15:49     ` Peter Zijlstra
2010-12-07 15:59       ` Nick Piggin
2010-12-07 16:23         ` Peter Zijlstra
2010-12-08  3:28     ` Nick Piggin
2010-12-07 21:56 ` Dave Chinner
2010-12-08  1:47   ` Nick Piggin
2010-12-08  3:32     ` Dave Chinner
2010-12-08  4:28       ` Dave Chinner
2010-12-08  7:09         ` Nick Piggin
2010-12-10 20:32           ` Paul E. McKenney
2010-12-12 14:54             ` Paul E. McKenney

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=8cbc64c4c8ab6be0ae5a7fa00ebabc7a8d60641a.1290852960.git.npiggin@kernel.dk \
    --to=npiggin@kernel.dk \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®