Skip to contentSkip to conversation

Permit filesystem local caching

PATCH In review David Howells 3 participants 44 messages Feb 8, 2008 – Feb 11, 2008

Subsystems (65)
lore
Share & tools
lore

David Howells

author maintainer
#0 lore raw

cover Permit filesystem local caching

These patches add local caching for network filesystems such as NFS.

The patches can roughly be broken down into a number of sets:

(*) 01-keys-inc-payload.diff
(*) 02-keys-search-keyring.diff
(*) 03-keys-callout-blob.diff

Three patches to the keyring code made to help the CIFS people. Included because of patches 05-08.

(*) 04-keys-get-label.diff

A patch to allow the security label of a key to be retrieved. Included because of patches 05-08.

(*) 05-security-current-fsugid.diff
(*) 06-security-separate-task-bits.diff
(*) 07-security-subjective.diff
(*) 08-security-kernel_service-class.diff
(*) 09-security-kernel-service.diff
(*) 10-security-nfsd.diff

Patches to permit the subjective security of a task to be overridden. All the security details in task_struct are decanted into a new struct that task_struct then has two pointers two: one that defines the objective security of that task (how other tasks may affect it) and one that defines the subjective security (how it may affect other objects).

Note that I have dropped the idea of struct cred for the moment. With the amount of stuff that was excluded from it, it wasn't actually any use to me. However, it can be added later.

Required for cachefiles.

(*) 11-release-page.diff
(*) 12-fscache-page-flags.diff
(*) 13-add_wait_queue_tail.diff
(*) 14-fscache.diff

Patches to provide a local caching facility for network filesystems.

(*) 15-cachefiles-ia64.diff
(*) 16-cachefiles-ext3-f_mapping.diff
(*) 17-cachefiles-write.diff
(*) 18-cachefiles-monitor.diff
(*) 19-cachefiles-export.diff
(*) 20-cachefiles.diff

Patches to provide a local cache in a directory of an already mounted filesystem.

(*) 21-nfs-comment.diff
(*) 22-nfs-fscache-option.diff
(*) 23-nfs-fscache-kconfig.diff
(*) 24-nfs-fscache-top-index.diff
(*) 25-nfs-fscache-server-obj.diff
(*) 26-nfs-fscache-super-obj.diff
(*) 27-nfs-fscache-inode-obj.diff
(*) 28-nfs-fscache-use-inode.diff
(*) 29-nfs-fscache-invalidate-pages.diff
(*) 30-nfs-fscache-iostats.diff
(*) 31-nfs-fscache-page-management.diff
(*) 32-nfs-fscache-read-context.diff
(*) 33-nfs-fscache-read-fallback.diff
(*) 34-nfs-fscache-read-from-cache.diff
(*) 35-nfs-fscache-store-to-cache.diff
(*) 36-nfs-fscache-mount.diff
(*) 37-nfs-fscache-display.diff

Patches to provide NFS with local caching.

A couple of questions on the NFS iostat changes: (1) Should I update the iostat version number; (2) is it permitted to have conditional iostats?

I've massively split up the NFS patches as requested by Trond Myklebust and Chuck Lever. I've also brought the patches up to date with the patch window turbulence.

--
A tarball of the patches is available at:

http://people.redhat.com/~dhowells/fscache/patches/nfs+fscache-29.tar.bz2

To use this version of CacheFiles, the cachefilesd-0.9 is also required. It is available as an SRPM:

	http://people.redhat.com/~dhowells/fscache/cachefilesd-0.9-1.fc7.src.rpm

Or as individual bits:

http://people.redhat.com/~dhowells/fscache/cachefilesd-0.9.tar.bz2
http://people.redhat.com/~dhowells/fscache/cachefilesd.fc
http://people.redhat.com/~dhowells/fscache/cachefilesd.if
http://people.redhat.com/~dhowells/fscache/cachefilesd.te
http://people.redhat.com/~dhowells/fscache/cachefilesd.spec

The .fc, .if and .te files are for manipulating SELinux.

David

author maintainer
#1 lore raw

PATCH 1/37 KEYS: Increase the payload size when instantiating a key

Increase the size of a payload that can be used to instantiate a key in add_key() and keyctl_instantiate_key(). This permits huge CIFS SPNEGO blobs to be passed around. The limit is raised to 1MB. If kmalloc() can't allocate a buffer of sufficient size, vmalloc() will be tried instead.

---

 security/keys/keyctl.c |   38 ++++++++++++++++++++++++++++++--------
 1 files changed, 30 insertions(+), 8 deletions(-)
security/keys/keyctl.c +30 -8
index d9ca15c..8ec8432 100644
@@ -19,6 +19,7 @@
 #include <linux/capability.h>
 #include <linux/string.h>
 #include <linux/err.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -62,9 +63,10 @@ asmlinkage long sys_add_key(const char __user *_type,
 	char type[32], *description;
 	void *payload;
 	long ret;
+	bool vm;
 
 	ret = -EINVAL;
-	if (plen > 32767)
+	if (plen > 1024 * 1024 - 1)
 		goto error;
 
 	/* draw all the data into kernel space */
@@ -81,11 +83,18 @@ asmlinkage long sys_add_key(const char __user *_type,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
+	vm = false;
 	if (_payload) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
-		if (!payload)
-			goto error2;
+		if (!payload) {
+			if (plen <= PAGE_SIZE)
+				goto error2;
+			vm = true;
+			payload = vmalloc(plen);
+			if (!payload)
+				goto error2;
+		}
 
 		ret = -EFAULT;
 		if (copy_from_user(payload, _payload, plen) != 0)
@@ -113,7 +122,10 @@ asmlinkage long sys_add_key(const char __user *_type,
 
 	key_ref_put(keyring_ref);
  error3:
-	kfree(payload);
+	if (!vm)
+		kfree(payload);
+	else
+		vfree(payload);
  error2:
 	kfree(description);
  error:
@@ -821,9 +833,10 @@ long keyctl_instantiate_key(key_serial_t id,
 	key_ref_t keyring_ref;
 	void *payload;
 	long ret;
+	bool vm = false;
 
 	ret = -EINVAL;
-	if (plen > 32767)
+	if (plen > 1024 * 1024 - 1)
 		goto error;
 
 	/* the appropriate instantiation authorisation key must have been
@@ -843,8 +856,14 @@ long keyctl_instantiate_key(key_serial_t id,
 	if (_payload) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
-		if (!payload)
-			goto error;
+		if (!payload) {
+			if (plen <= PAGE_SIZE)
+				goto error;
+			vm = true;
+			payload = vmalloc(plen);
+			if (!payload)
+				goto error;
+		}
 
 		ret = -EFAULT;
 		if (copy_from_user(payload, _payload, plen) != 0)
@@ -877,7 +896,10 @@ long keyctl_instantiate_key(key_serial_t id,
 	}
 
 error2:
-	kfree(payload);
+	if (!vm)
+		kfree(payload);
+	else
+		vfree(payload);
 error:
 	return ret;
author maintainer
#2 lore raw

PATCH 2/37 KEYS: Check starting keyring as part of search

In reply to David Howells

Check the starting keyring as part of the search to (a) see if that is what we're searching for, and (b) to check it is still valid for searching.

The scenario: User in process A does things that cause things to be created in its process session keyring. The user then does an su to another user and starts a new process, B. The two processes now share the same process session keyring.

Process B does an NFS access which results in an upcall to gssd. When gssd attempts to instantiate the context key (to be linked into the process session keyring), it is denied access even though it has an authorization key.

The order of calls is:

keyctl_instantiate_key()
lookup_user_key() (the default: case)
search_process_keyrings(current)
search_process_keyrings(rka->context) (recursive call)
keyring_search_aux()

keyring_search_aux() verifies the keys and keyrings underneath the top-level keyring it is given, but that top-level keyring is neither fully validated nor checked to see if it is the thing being searched for.

This patch changes keyring_search_aux() to:
1) do more validation on the top keyring it is given and
2) check whether that top-level keyring is the thing being searched for

---

 security/keys/keyring.c |   35 +++++++++++++++++++++++++++++++----
 1 files changed, 31 insertions(+), 4 deletions(-)
security/keys/keyring.c +31 -4
index 88292e3..76b89b2 100644
@@ -292,7 +292,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	struct keyring_list *keylist;
 	struct timespec now;
-	unsigned long possessed;
+	unsigned long possessed, kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
 	long err;
@@ -318,6 +318,32 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	now = current_kernel_time();
 	err = -EAGAIN;
 	sp = 0;
+	
+	/* firstly we should check to see if this top-level keyring is what we
+	 * are looking for */
+	key_ref = ERR_PTR(-EAGAIN);
+	kflags = keyring->flags;
+	if (keyring->type == type && match(keyring, description)) {
+		key = keyring;
+
+		/* check it isn't negative and hasn't expired or been
+		 * revoked */
+		if (kflags & (1 << KEY_FLAG_REVOKED))
+			goto error_2;
+		if (key->expiry && now.tv_sec >= key->expiry)
+			goto error_2;
+		key_ref = ERR_PTR(-ENOKEY);
+		if (kflags & (1 << KEY_FLAG_NEGATIVE))
+			goto error_2;
+		goto found;
+	}
+
+	/* otherwise, the top keyring must not be revoked, expired, or
+	 * negatively instantiated if we are to search it */
+	key_ref = ERR_PTR(-EAGAIN);
+	if (kflags & ((1 << KEY_FLAG_REVOKED) | (1 << KEY_FLAG_NEGATIVE)) ||
+	    (keyring->expiry && now.tv_sec >= keyring->expiry))
+		goto error_2;
 
 	/* start processing a new keyring */
 descend:
@@ -331,13 +357,14 @@ descend:
 	/* iterate through the keys in this keyring first */
 	for (kix = 0; kix < keylist->nkeys; kix++) {
 		key = keylist->keys[kix];
+		kflags = key->flags;
 
 		/* ignore keys not of this type */
 		if (key->type != type)
 			continue;
 
 		/* skip revoked keys and expired keys */
-		if (test_bit(KEY_FLAG_REVOKED, &key->flags))
+		if (kflags & (1 << KEY_FLAG_REVOKED))
 			continue;
 
 		if (key->expiry && now.tv_sec >= key->expiry)
@@ -352,8 +379,8 @@ descend:
 					context, KEY_SEARCH) < 0)
 			continue;
 
-		/* we set a different error code if we find a negative key */
-		if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+		/* we set a different error code if we pass a negative key */
+		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
 			err = -ENOKEY;
 			continue;
 		}
author maintainer
#3 lore raw

PATCH 3/37 KEYS: Allow the callout data to be passed as a blob rather than a string

In reply to David Howells

Allow the callout data to be passed as a blob rather than a string for internal kernel services that call any request_key_*() interface other than request_key(). request_key() itself still takes a NUL-terminated string.

The functions that change are:

request_key_with_auxdata()
request_key_async()
request_key_async_with_auxdata()

---

 Documentation/keys-request-key.txt |   11 +++++---
 Documentation/keys.txt             |   14 +++++++---
 include/linux/key.h                |    9 ++++---
 security/keys/internal.h           |    9 ++++---
 security/keys/keyctl.c             |    7 ++++-
 security/keys/request_key.c        |   49 ++++++++++++++++++++++--------------
 security/keys/request_key_auth.c   |   12 +++++----
 7 files changed, 70 insertions(+), 41 deletions(-)
Documentation/keys-request-key.txt +7 -4
index 266955d..09b55e4 100644
@@ -11,26 +11,29 @@ request_key*():
 
 	struct key *request_key(const struct key_type *type,
 				const char *description,
-				const char *callout_string);
+				const char *callout_info);
 
 or:
 
 	struct key *request_key_with_auxdata(const struct key_type *type,
 					     const char *description,
-					     const char *callout_string,
+					     const char *callout_info,
+					     size_t callout_len,
 					     void *aux);
 
 or:
 
 	struct key *request_key_async(const struct key_type *type,
 				      const char *description,
-				      const char *callout_string);
+				      const char *callout_info,
+				      size_t callout_len);
 
 or:
 
 	struct key *request_key_async_with_auxdata(const struct key_type *type,
 						   const char *description,
-						   const char *callout_string,
+						   const char *callout_info,
+					     	   size_t callout_len,
 						   void *aux);
 
 Or by userspace invoking the request_key system call:
Documentation/keys.txt +9 -5
index 51652d3..b82d38d 100644
@@ -771,7 +771,7 @@ payload contents" for more information.
 
 	struct key *request_key(const struct key_type *type,
 				const char *description,
-				const char *callout_string);
+				const char *callout_info);
 
     This is used to request a key or keyring with a description that matches
     the description specified according to the key type's match function. This
@@ -793,24 +793,28 @@ payload contents" for more information.
 
 	struct key *request_key_with_auxdata(const struct key_type *type,
 					     const char *description,
-					     const char *callout_string,
+					     const void *callout_info,
+					     size_t callout_len,
 					     void *aux);
 
     This is identical to request_key(), except that the auxiliary data is
-    passed to the key_type->request_key() op if it exists.
+    passed to the key_type->request_key() op if it exists, and the callout_info
+    is a blob of length callout_len, if given (the length may be 0).
 
 
 (*) A key can be requested asynchronously by calling one of:
 
 	struct key *request_key_async(const struct key_type *type,
 				      const char *description,
-				      const char *callout_string);
+				      const void *callout_info,
+				      size_t callout_len);
 
     or:
 
 	struct key *request_key_async_with_auxdata(const struct key_type *type,
 						   const char *description,
-						   const char *callout_string,
+						   const char *callout_info,
+					     	   size_t callout_len,
 					     	   void *aux);
 
     which are asynchronous equivalents of request_key() and
include/linux/key.h +6 -3
index a70b8a8..163f864 100644
@@ -208,16 +208,19 @@ extern struct key *request_key(struct key_type *type,
 
 extern struct key *request_key_with_auxdata(struct key_type *type,
 					    const char *description,
-					    const char *callout_info,
+					    const void *callout_info,
+					    size_t callout_len,
 					    void *aux);
 
 extern struct key *request_key_async(struct key_type *type,
 				     const char *description,
-				     const char *callout_info);
+				     const void *callout_info,
+				     size_t callout_len);
 
 extern struct key *request_key_async_with_auxdata(struct key_type *type,
 						  const char *description,
-						  const char *callout_info,
+						  const void *callout_info,
+						  size_t callout_len,
 						  void *aux);
 
 extern int wait_for_key_construction(struct key *key, bool intr);
security/keys/internal.h +6 -3
index d36d693..f004835 100644
@@ -109,7 +109,8 @@ extern int install_process_keyring(struct task_struct *tsk);
 
 extern struct key *request_key_and_link(struct key_type *type,
 					const char *description,
-					const char *callout_info,
+					const void *callout_info,
+					size_t callout_len,
 					void *aux,
 					struct key *dest_keyring,
 					unsigned long flags);
@@ -120,13 +121,15 @@ extern struct key *request_key_and_link(struct key_type *type,
 struct request_key_auth {
 	struct key		*target_key;
 	struct task_struct	*context;
-	char			*callout_info;
+	void			*callout_info;
+	size_t			callout_len;
 	pid_t			pid;
 };
 
 extern struct key_type key_type_request_key_auth;
 extern struct key *request_key_auth_new(struct key *target,
-					const char *callout_info);
+					const void *callout_info,
+					size_t callout_len);
 
 extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
 
security/keys/keyctl.c +5 -2
index 8ec8432..1698bf9 100644
@@ -152,6 +152,7 @@ asmlinkage long sys_request_key(const char __user *_type,
 	struct key_type *ktype;
 	struct key *key;
 	key_ref_t dest_ref;
+	size_t callout_len;
 	char type[32], *description, *callout_info;
 	long ret;
 
@@ -169,12 +170,14 @@ asmlinkage long sys_request_key(const char __user *_type,
 
 	/* pull the callout info into kernel space */
 	callout_info = NULL;
+	callout_len = 0;
 	if (_callout_info) {
 		callout_info = strndup_user(_callout_info, PAGE_SIZE);
 		if (IS_ERR(callout_info)) {
 			ret = PTR_ERR(callout_info);
 			goto error2;
 		}
+		callout_len = strlen(callout_info);
 	}
 
 	/* get the destination keyring if specified */
@@ -195,8 +198,8 @@ asmlinkage long sys_request_key(const char __user *_type,
 	}
 
 	/* do the search */
-	key = request_key_and_link(ktype, description, callout_info, NULL,
-				   key_ref_to_ptr(dest_ref),
+	key = request_key_and_link(ktype, description, callout_info,
+				   callout_len, NULL, key_ref_to_ptr(dest_ref),
 				   KEY_ALLOC_IN_QUOTA);
 	if (IS_ERR(key)) {
 		ret = PTR_ERR(key);
security/keys/request_key.c +30 -19

130 lines not on this page · raw message

security/keys/request_key_auth.c +7 -5
index e42b525..c615d47 100644
@@ -61,7 +61,7 @@ static void request_key_auth_describe(const struct key *key,
 
 	seq_puts(m, "key:");
 	seq_puts(m, key->description);
-	seq_printf(m, " pid:%d ci:%zu", rka->pid, strlen(rka->callout_info));
+	seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len);
 
 } /* end request_key_auth_describe() */
 
@@ -77,7 +77,7 @@ static long request_key_auth_read(const struct key *key,
 	size_t datalen;
 	long ret;
 
-	datalen = strlen(rka->callout_info);
+	datalen = rka->callout_len;
 	ret = datalen;
 
 	/* we can return the data as is */
@@ -137,7 +137,8 @@ static void request_key_auth_destroy(struct key *key)
  * create an authorisation token for /sbin/request-key or whoever to gain
  * access to the caller's security data
  */
-struct key *request_key_auth_new(struct key *target, const char *callout_info)
+struct key *request_key_auth_new(struct key *target, const void *callout_info,
+				 size_t callout_len)
 {
 	struct request_key_auth *rka, *irka;
 	struct key *authkey = NULL;
@@ -152,7 +153,7 @@ struct key *request_key_auth_new(struct key *target, const char *callout_info)
 		kleave(" = -ENOMEM");
 		return ERR_PTR(-ENOMEM);
 	}
-	rka->callout_info = kmalloc(strlen(callout_info) + 1, GFP_KERNEL);
+	rka->callout_info = kmalloc(callout_len, GFP_KERNEL);
 	if (!rka->callout_info) {
 		kleave(" = -ENOMEM");
 		kfree(rka);
@@ -186,7 +187,8 @@ struct key *request_key_auth_new(struct key *target, const char *callout_info)
 	}
 
 	rka->target_key = key_get(target);
-	strcpy(rka->callout_info, callout_info);
+	memcpy(rka->callout_info, callout_info, callout_len);
+	rka->callout_len = callout_len;
 
 	/* allocate the auth key */
 	sprintf(desc, "%x", target->serial);
author maintainer
#4 lore raw

PATCH 4/37 KEYS: Add keyctl function to get a security label

In reply to David Howells

Add a keyctl() function to get the security label of a key.

The following is added to Documentation/keys.txt:

(*) Get the LSM security context attached to a key.

long keyctl(KEYCTL_GET_SECURITY, key_serial_t key, char *buffer,
size_t buflen)

This function returns a string that represents the LSM security context attached to a key in the buffer provided.

Unless there's an error, it always returns the amount of data it could produce, even if that's too big for the buffer, but it won't copy more than requested to userspace. If the buffer pointer is NULL then no copy will take place.

A NUL character is included at the end of the string if the buffer is sufficiently big. This is included in the returned count. If no LSM is in force then an empty string will be returned.

A process must have view permission on the key for this function to be successful.

---

 Documentation/keys.txt   |   21 +++++++++++++++
 include/linux/keyctl.h   |    1 +
 include/linux/security.h |   20 +++++++++++++-
 security/dummy.c         |    8 ++++++
 security/keys/compat.c   |    3 ++
 security/keys/keyctl.c   |   66 ++++++++++++++++++++++++++++++++++++++++++++++
 security/security.c      |    5 +++
 security/selinux/hooks.c |   21 +++++++++++++--
 8 files changed, 141 insertions(+), 4 deletions(-)
Documentation/keys.txt +21 -0
index b82d38d..be424b0 100644
@@ -711,6 +711,27 @@ The keyctl syscall functions are:
      The assumed authoritative key is inherited across fork and exec.
 
 
+ (*) Get the LSM security context attached to a key.
+
+	long keyctl(KEYCTL_GET_SECURITY, key_serial_t key, char *buffer,
+		    size_t buflen)
+
+     This function returns a string that represents the LSM security context
+     attached to a key in the buffer provided.
+
+     Unless there's an error, it always returns the amount of data it could
+     produce, even if that's too big for the buffer, but it won't copy more
+     than requested to userspace. If the buffer pointer is NULL then no copy
+     will take place.
+
+     A NUL character is included at the end of the string if the buffer is
+     sufficiently big.  This is included in the returned count.  If no LSM is
+     in force then an empty string will be returned.
+
+     A process must have view permission on the key for this function to be
+     successful.
+
+
 ===============
 KERNEL SERVICES
 ===============
include/linux/keyctl.h +1 -0
index 3365945..656ee6b 100644
@@ -49,5 +49,6 @@
 #define KEYCTL_SET_REQKEY_KEYRING	14	/* set default request-key keyring */
 #define KEYCTL_SET_TIMEOUT		15	/* set key timeout */
 #define KEYCTL_ASSUME_AUTHORITY		16	/* assume request_key() authorisation */
+#define KEYCTL_GET_SECURITY		17	/* get key security label */
 
 #endif /*  _LINUX_KEYCTL_H */
include/linux/security.h +19 -1
index fe52cde..a33fd03 100644
@@ -970,6 +970,17 @@ struct request_sock;
  *	@perm describes the combination of permissions required of this key.
  *	Return 1 if permission granted, 0 if permission denied and -ve it the
  *      normal permissions model should be effected.
+ * @key_getsecurity:
+ *	Get a textual representation of the security context attached to a key
+ *	for the purposes of honouring KEYCTL_GETSECURITY.  This function
+ *	allocates the storage for the NUL-terminated string and the caller
+ *	should free it.
+ *	@key points to the key to be queried.
+ *	@_buffer points to a pointer that should be set to point to the
+ *	 resulting string (if no label or an error occurs).
+ *	Return the length of the string (including terminating NUL) or -ve if
+ *      an error.
+ *	May also return 0 (and a NULL buffer pointer) if there is no label.
  *
  * Security hooks affecting all System V IPC operations.
  *
@@ -1459,7 +1470,7 @@ struct security_operations {
 	int (*key_permission)(key_ref_t key_ref,
 			      struct task_struct *context,
 			      key_perm_t perm);
-
+	int (*key_getsecurity)(struct key *key, char **_buffer);
 #endif	/* CONFIG_KEYS */
 
 };
@@ -2600,6 +2611,7 @@ int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long f
 void security_key_free(struct key *key);
 int security_key_permission(key_ref_t key_ref,
 			    struct task_struct *context, key_perm_t perm);
+int security_key_getsecurity(struct key *key, char **_buffer);
 
 #else
 
@@ -2621,6 +2633,12 @@ static inline int security_key_permission(key_ref_t key_ref,
 	return 0;
 }
 
+static inline int security_key_getsecurity(struct key *key, char **_buffer)
+{
+	*_buffer = NULL;
+	return 0;
+}
+
 #endif
 #endif /* CONFIG_KEYS */
 
security/dummy.c +8 -0
index 649326b..6a0056b 100644
@@ -977,6 +977,13 @@ static inline int dummy_key_permission(key_ref_t key_ref,
 {
 	return 0;
 }
+
+static int dummy_key_getsecurity(struct key *key, char **_buffer)
+{
+	*_buffer = NULL;
+	return 0;
+}
+
 #endif /* CONFIG_KEYS */
 
 struct security_operations dummy_security_ops;
@@ -1164,6 +1171,7 @@ void security_fixup_ops (struct security_operations *ops)
 	set_to_dummy_if_null(ops, key_alloc);
 	set_to_dummy_if_null(ops, key_free);
 	set_to_dummy_if_null(ops, key_permission);
+	set_to_dummy_if_null(ops, key_getsecurity);
 #endif	/* CONFIG_KEYS */
 
 }
security/keys/compat.c +3 -0
index e10ec99..c766c68 100644
@@ -79,6 +79,9 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_ASSUME_AUTHORITY:
 		return keyctl_assume_authority(arg2);
 
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security(arg2, compat_ptr(arg3), arg4);
+
 	default:
 		return -EOPNOTSUPP;
 	}
security/keys/keyctl.c +66 -0

84 lines not on this page · raw message

security/security.c +5 -0
index d15e56c..3e75b90 100644
@@ -1102,4 +1102,9 @@ int security_key_permission(key_ref_t key_ref,
 	return security_ops->key_permission(key_ref, context, perm);
 }
 
+int security_key_getsecurity(struct key *key, char **_buffer)
+{
+	return security_ops->key_getsecurity(key, _buffer);
+}
+
 #endif	/* CONFIG_KEYS */
security/selinux/hooks.c +18 -3
index e5ed075..face4b4 100644
@@ -5203,6 +5203,20 @@ static int selinux_key_permission(key_ref_t key_ref,
 			    SECCLASS_KEY, perm, NULL);
 }
 
+static int selinux_key_getsecurity(struct key *key, char **_buffer)
+{
+	struct key_security_struct *ksec = key->security;
+	char *context = NULL;
+	unsigned len;
+	int rc;
+
+	rc = security_sid_to_context(ksec->sid, &context, &len);
+	if (!rc)
+		rc = len;
+	*_buffer = context;
+	return rc;
+}
+
 #endif
 
 static struct security_operations selinux_ops = {
@@ -5382,9 +5396,10 @@ static struct security_operations selinux_ops = {
 #endif
 
 #ifdef CONFIG_KEYS
-	.key_alloc =                    selinux_key_alloc,
-	.key_free =                     selinux_key_free,
-	.key_permission =               selinux_key_permission,
+	.key_alloc =			selinux_key_alloc,
+	.key_free =			selinux_key_free,
+	.key_permission =		selinux_key_permission,
+	.key_getsecurity =		selinux_key_getsecurity,
 #endif
 };
author maintainer
#5 lore raw

PATCH 5/37 Security: Change current->fs[ug]id to current_fs[ug]id()

In reply to David Howells

Change current->fs[ug]id to current_fs[ug]id() so that fsgid and fsuid can be separated from the task_struct.

---

 arch/ia64/kernel/perfmon.c                |    4 ++--
 arch/powerpc/platforms/cell/spufs/inode.c |    4 ++--
 drivers/isdn/capi/capifs.c                |    4 ++--
 drivers/usb/core/inode.c                  |    4 ++--
 fs/9p/fid.c                               |    2 +-
 fs/9p/vfs_inode.c                         |    4 ++--
 fs/9p/vfs_super.c                         |    4 ++--
 fs/affs/inode.c                           |    4 ++--
 fs/anon_inodes.c                          |    4 ++--
 fs/attr.c                                 |    4 ++--
 fs/bfs/dir.c                              |    4 ++--
 fs/cifs/cifsproto.h                       |    2 +-
 fs/cifs/dir.c                             |   12 ++++++------
 fs/cifs/inode.c                           |    8 ++++----
 fs/cifs/misc.c                            |    4 ++--
 fs/coda/cache.c                           |    6 +++---
 fs/coda/upcall.c                          |    4 ++--
 fs/devpts/inode.c                         |    4 ++--
 fs/dquot.c                                |    2 +-
 fs/exec.c                                 |    4 ++--
 fs/ext2/balloc.c                          |    2 +-
 fs/ext2/ialloc.c                          |    4 ++--
 fs/ext2/ioctl.c                           |    2 +-
 fs/ext3/balloc.c                          |    2 +-
 fs/ext3/ialloc.c                          |    4 ++--
 fs/ext4/balloc.c                          |    2 +-
 fs/ext4/ialloc.c                          |    4 ++--
 fs/fuse/dev.c                             |    4 ++--
 fs/gfs2/inode.c                           |   10 +++++-----
 fs/hfs/inode.c                            |    4 ++--
 fs/hfsplus/inode.c                        |    4 ++--
 fs/hpfs/namei.c                           |   24 ++++++++++++------------
 fs/hugetlbfs/inode.c                      |   16 ++++++++--------
 fs/jffs2/fs.c                             |    4 ++--
 fs/jfs/jfs_inode.c                        |    4 ++--
 fs/locks.c                                |    2 +-
 fs/minix/bitmap.c                         |    4 ++--
 fs/namei.c                                |    8 ++++----
 fs/nfsd/vfs.c                             |    4 ++--
 fs/ocfs2/dlm/dlmfs.c                      |    8 ++++----
 fs/ocfs2/namei.c                          |    4 ++--
 fs/pipe.c                                 |    4 ++--
 fs/posix_acl.c                            |    4 ++--
 fs/ramfs/inode.c                          |    4 ++--
 fs/reiserfs/namei.c                       |    4 ++--
 fs/sysv/ialloc.c                          |    4 ++--
 fs/udf/ialloc.c                           |    4 ++--
 fs/udf/namei.c                            |    2 +-
 fs/ufs/ialloc.c                           |    4 ++--
 fs/xfs/linux-2.6/xfs_linux.h              |    4 ++--
 fs/xfs/xfs_acl.c                          |    6 +++---
 fs/xfs/xfs_attr.c                         |    2 +-
 fs/xfs/xfs_inode.c                        |    4 ++--
 fs/xfs/xfs_vnodeops.c                     |    8 ++++----
 include/linux/fs.h                        |    2 +-
 include/linux/sched.h                     |    3 +++
 ipc/mqueue.c                              |    4 ++--
 kernel/cgroup.c                           |    4 ++--
 mm/shmem.c                                |    8 ++++----
 net/9p/client.c                           |    2 +-
 net/socket.c                              |    4 ++--
 net/sunrpc/auth.c                         |    8 ++++----
 security/commoncap.c                      |    4 ++--
 security/keys/key.c                       |    2 +-
 security/keys/keyctl.c                    |    2 +-
 security/keys/request_key.c               |   10 +++++-----
 security/keys/request_key_auth.c          |    2 +-
 67 files changed, 160 insertions(+), 157 deletions(-)
arch/ia64/kernel/perfmon.c +2 -2
index 78acd9f..9ef832c 100644
@@ -2206,8 +2206,8 @@ pfm_alloc_fd(struct file **cfile)
 	DPRINT(("new inode ino=%ld @%p\n", inode->i_ino, inode));
 
 	inode->i_mode = S_IFCHR|S_IRUGO;
-	inode->i_uid  = current->fsuid;
-	inode->i_gid  = current->fsgid;
+	inode->i_uid  = current_fsuid();
+	inode->i_gid  = current_fsgid();
 
 	sprintf(name, "[%lu]", inode->i_ino);
 	this.name = name;
arch/powerpc/platforms/cell/spufs/inode.c +2 -2
index 90784c0..0c3838c 100644
@@ -85,8 +85,8 @@ spufs_new_inode(struct super_block *sb, int mode)
 		goto out;
 
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_blocks = 0;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 out:
drivers/isdn/capi/capifs.c +2 -2
index 2dd1b57..26b9aea 100644
@@ -148,8 +148,8 @@ void capifs_new_ncci(unsigned int number, dev_t device)
 	if (!inode)
 		return;
 	inode->i_ino = number+2;
-	inode->i_uid = config.setuid ? config.uid : current->fsuid;
-	inode->i_gid = config.setgid ? config.gid : current->fsgid;
+	inode->i_uid = config.setuid ? config.uid : current_fsuid();
+	inode->i_gid = config.setgid ? config.gid : current_fsgid();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	init_special_inode(inode, S_IFCHR|config.mode, device);
 	//inode->i_op = &capifs_file_inode_operations;
drivers/usb/core/inode.c +2 -2
index 83a373e..80edcb5 100644
@@ -275,8 +275,8 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de
 
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		switch (mode & S_IFMT) {
fs/9p/fid.c +1 -1
index dfebdbe..eca17e4 100644
@@ -121,7 +121,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 	switch (access) {
 	case V9FS_ACCESS_SINGLE:
 	case V9FS_ACCESS_USER:
-		uid = current->fsuid;
+		uid = current_fsuid();
 		any = 0;
 		break;
 
fs/9p/vfs_inode.c +2 -2
index 6a28842..f028d80 100644
@@ -207,8 +207,8 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 	inode = new_inode(sb);
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_rdev = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
fs/9p/vfs_super.c +2 -2
index 678c02f..465520d 100644
@@ -112,8 +112,8 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 	struct v9fs_session_info *v9ses = NULL;
 	struct p9_stat *st = NULL;
 	int mode = S_IRWXUGO | S_ISVTX;
-	uid_t uid = current->fsuid;
-	gid_t gid = current->fsgid;
+	uid_t uid = current_fsuid();
+	gid_t gid = current_fsgid();
 	struct p9_fid *fid;
 	int retval = 0;
 
fs/affs/inode.c +2 -2
index 27fe6cb..3e10915 100644
@@ -311,8 +311,8 @@ affs_new_inode(struct inode *dir)
 	mark_buffer_dirty_inode(bh, inode);
 	affs_brelse(bh);
 
-	inode->i_uid     = current->fsuid;
-	inode->i_gid     = current->fsgid;
+	inode->i_uid     = current_fsuid();
+	inode->i_gid     = current_fsgid();
 	inode->i_ino     = block;
 	inode->i_nlink   = 1;
 	inode->i_mtime   = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
fs/anon_inodes.c +2 -2
index 2332188..a2f6a13 100644
@@ -162,8 +162,8 @@ static struct inode *anon_inode_mkinode(void)
 	 */
 	inode->i_state = I_DIRTY;
 	inode->i_mode = S_IRUSR | S_IWUSR;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	return inode;
 }
fs/attr.c +2 -2
index 966b73e..117cca7 100644
@@ -29,13 +29,13 @@ int inode_change_ok(struct inode *inode, struct iattr *attr)
 
 	/* Make sure a caller can chown. */
 	if ((ia_valid & ATTR_UID) &&
-	    (current->fsuid != inode->i_uid ||
+	    (current_fsuid() != inode->i_uid ||
 	     attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN))
 		goto error;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
-	    (current->fsuid != inode->i_uid ||
+	    (current_fsuid() != inode->i_uid ||
 	    (!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) &&
 	    !capable(CAP_CHOWN))
 		goto error;
fs/bfs/dir.c +2 -2
index 034950c..b8b5ae3 100644
@@ -104,8 +104,8 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	}
 	set_bit(ino, info->si_imap);
 	info->si_freei--;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	inode->i_blocks = 0;
 	inode->i_op = &bfs_file_inops;
fs/cifs/cifsproto.h +1 -1
index 2f09f56..d0f14d2 100644
@@ -39,7 +39,7 @@ extern int smb_send(struct socket *, struct smb_hdr *,
 			unsigned int /* length */ , struct sockaddr *);
 extern unsigned int _GetXid(void);
 extern void _FreeXid(unsigned int);
-#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__FUNCTION__, xid,current->fsuid));
+#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__FUNCTION__, xid,current_fsuid()));
 #define FreeXid(curr_xid) {_FreeXid(curr_xid); cFYI(1,("CIFS VFS: leaving %s (xid = %d) rc = %d",__FUNCTION__,curr_xid,(int)rc));}
 extern char *build_path_from_dentry(struct dentry *);
 extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
fs/cifs/dir.c +6 -6
index 699ec11..90cd8ef 100644
@@ -211,8 +211,8 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
 			mode &= ~current->fs->umask;
 			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 				CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode,
-					(__u64)current->fsuid,
-					(__u64)current->fsgid,
+					(__u64)current_fsuid(),
+					(__u64)current_fsgid(),
 					0 /* dev */,
 					cifs_sb->local_nls,
 					cifs_sb->mnt_cifs_flags &
@@ -246,8 +246,8 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
 				if ((oplock & CIFS_CREATE_ACTION) &&
 				    (cifs_sb->mnt_cifs_flags &
 				     CIFS_MOUNT_SET_UID)) {
-					newinode->i_uid = current->fsuid;
-					newinode->i_gid = current->fsgid;
+					newinode->i_uid = current_fsuid();
+					newinode->i_gid = current_fsgid();
 				}
 			}
 		}
@@ -340,8 +340,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 		mode &= ~current->fs->umask;
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 			rc = CIFSSMBUnixSetPerms(xid, pTcon, full_path,
-				mode, (__u64)current->fsuid,
-				(__u64)current->fsgid,
+				mode, (__u64)current_fsuid(),
+				(__u64)current_fsgid(),
 				device_number, cifs_sb->local_nls,
 				cifs_sb->mnt_cifs_flags &
 					CIFS_MOUNT_MAP_SPECIAL_CHR);
fs/cifs/inode.c +4 -4
index b1a4a65..6b67161 100644
@@ -1048,8 +1048,8 @@ mkdir_get_info:
 			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 				CIFSSMBUnixSetPerms(xid, pTcon, full_path,
 						    mode,
-						    (__u64)current->fsuid,
-						    (__u64)current->fsgid,
+						    (__u64)current_fsuid(),
+						    (__u64)current_fsgid(),
 						    0 /* dev_t */,
 						    cifs_sb->local_nls,
 						    cifs_sb->mnt_cifs_flags &
@@ -1072,9 +1072,9 @@ mkdir_get_info:
 				if (cifs_sb->mnt_cifs_flags &
 				     CIFS_MOUNT_SET_UID) {
 					direntry->d_inode->i_uid =
-						current->fsuid;
+						current_fsuid();
 					direntry->d_inode->i_gid =
-						current->fsgid;
+						current_fsgid();
 				}
 			}
 		}
fs/cifs/misc.c +2 -2
index 15546c2..b862231 100644
@@ -351,13 +351,13 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 		/*  BB Add support for establishing new tCon and SMB Session  */
 		/*      with userid/password pairs found on the smb session   */
 		/*	for other target tcp/ip addresses 		BB    */
-				if (current->fsuid != treeCon->ses->linux_uid) {
+				if (current_fsuid() != treeCon->ses->linux_uid) {
 					cFYI(1, ("Multiuser mode and UID "
 						 "did not match tcon uid"));
 					read_lock(&GlobalSMBSeslock);
 					list_for_each(temp_item, &GlobalSMBSessionList) {
 						ses = list_entry(temp_item, struct cifsSesInfo, cifsSessionList);
-						if (ses->linux_uid == current->fsuid) {
+						if (ses->linux_uid == current_fsuid()) {
 							if (ses->server == treeCon->ses->server) {
 								cFYI(1, ("found matching uid substitute right smb_uid"));
 								buffer->Uid = ses->Suid;
fs/coda/cache.c +3 -3
index 8a23703..a5bf577 100644
@@ -32,8 +32,8 @@ void coda_cache_enter(struct inode *inode, int mask)
 	struct coda_inode_info *cii = ITOC(inode);
 
 	cii->c_cached_epoch = atomic_read(&permission_epoch);
-	if (cii->c_uid != current->fsuid) {
-                cii->c_uid = current->fsuid;
+	if (cii->c_uid != current_fsuid()) {
+		cii->c_uid = current_fsuid();
                 cii->c_cached_perm = mask;
         } else
                 cii->c_cached_perm |= mask;
@@ -60,7 +60,7 @@ int coda_cache_check(struct inode *inode, int mask)
         int hit;
 	
         hit = (mask & cii->c_cached_perm) == mask &&
-		cii->c_uid == current->fsuid &&
+		cii->c_uid == current_fsuid() &&
 		cii->c_cached_epoch == atomic_read(&permission_epoch);
 
         return hit;
fs/coda/upcall.c +2 -2
index 359e531..806e6aa 100644
@@ -54,9 +54,9 @@ static void *alloc_upcall(int opcode, int size)
 	inp->ih.pgid = task_pgrp_nr(current);
 #ifdef CONFIG_CODA_FS_OLD_API
 	memset(&inp->ih.cred, 0, sizeof(struct coda_cred));
-	inp->ih.cred.cr_fsuid = current->fsuid;
+	inp->ih.cred.cr_fsuid = current_fsuid();
 #else
-	inp->ih.uid = current->fsuid;
+	inp->ih.uid = current_fsuid();
 #endif
 	return (void*)inp;
 }
fs/devpts/inode.c +2 -2
index 06ef9a2..1c9ffd9 100644
@@ -172,8 +172,8 @@ int devpts_pty_new(struct tty_struct *tty)
 		return -ENOMEM;
 
 	inode->i_ino = number+2;
-	inode->i_uid = config.setuid ? config.uid : current->fsuid;
-	inode->i_gid = config.setgid ? config.gid : current->fsgid;
+	inode->i_uid = config.setuid ? config.uid : current_fsuid();
+	inode->i_gid = config.setgid ? config.gid : current_fsgid();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	init_special_inode(inode, S_IFCHR|config.mode, device);
 	inode->i_private = tty;
fs/dquot.c +1 -1
index def4e96..bd1f666 100644
@@ -854,7 +854,7 @@ static inline int need_print_warning(struct dquot *dquot)
 
 	switch (dquot->dq_type) {
 		case USRQUOTA:
-			return current->fsuid == dquot->dq_id;
+			return current_fsuid() == dquot->dq_id;
 		case GRPQUOTA:
 			return in_group_p(dquot->dq_id);
 	}
fs/exec.c +2 -2
index be923e4..2516cb0 100644
@@ -1674,7 +1674,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 	struct inode * inode;
 	struct file * file;
 	int retval = 0;
-	int fsuid = current->fsuid;
+	int fsuid = current_fsuid();
 	int flag = 0;
 	int ispipe = 0;
 	unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
@@ -1780,7 +1780,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 	 * Dont allow local users get cute and trick others to coredump
 	 * into their pre-created files:
 	 */
-	if (inode->i_uid != current->fsuid)
+	if (inode->i_uid != current_fsuid())
 		goto close_fail;
 	if (!file->f_op)
 		goto close_fail;
fs/ext2/balloc.c +1 -1
index e7b2baf..5f7dd66 100644
@@ -1193,7 +1193,7 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
+		sbi->s_resuid != current_fsuid() &&
 		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
fs/ext2/ialloc.c +2 -2
index 5deb8b7..1d020a9 100644
@@ -554,7 +554,7 @@ got:
 
 	sb->s_dirt = 1;
 	mark_buffer_dirty(bh2);
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (test_opt (sb, GRPID))
 		inode->i_gid = dir->i_gid;
 	else if (dir->i_mode & S_ISGID) {
@@ -562,7 +562,7 @@ got:
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
 
 	inode->i_ino = ino;
fs/ext2/ioctl.c +1 -1
index b8ea11f..d52e7d9 100644
@@ -105,7 +105,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (IS_RDONLY(inode))
 			return -EROFS;
 
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+		if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
 			return -EACCES;
 
 		if (get_user(rsv_window_size, (int __user *)arg))
fs/ext3/balloc.c +1 -1
index a757130..9b5fad6 100644
@@ -1424,7 +1424,7 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
+		sbi->s_resuid != current_fsuid() &&
 		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
fs/ext3/ialloc.c +2 -2
index 58ae2f9..ad77546 100644
@@ -543,7 +543,7 @@ got:
 		percpu_counter_inc(&sbi->s_dirs_counter);
 	sb->s_dirt = 1;
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (test_opt (sb, GRPID))
 		inode->i_gid = dir->i_gid;
 	else if (dir->i_mode & S_ISGID) {
@@ -551,7 +551,7 @@ got:
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
 
 	inode->i_ino = ino;
fs/ext4/balloc.c +1 -1
index 0737e05..7bfd9b7 100644
@@ -1558,7 +1558,7 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi)
 	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
 	root_blocks = ext4_r_blocks_count(sbi->s_es);
 	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
+		sbi->s_resuid != current_fsuid() &&
 		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
 		return 0;
 	}
fs/ext4/ialloc.c +2 -2
index da18a74..f559991 100644
@@ -681,7 +681,7 @@ got:
 		percpu_counter_inc(&sbi->s_dirs_counter);
 	sb->s_dirt = 1;
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (test_opt (sb, GRPID))
 		inode->i_gid = dir->i_gid;
 	else if (dir->i_mode & S_ISGID) {
@@ -689,7 +689,7 @@ got:
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
 
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
fs/fuse/dev.c +2 -2
index af63980..e9c94ec 100644
@@ -79,8 +79,8 @@ static void __fuse_put_request(struct fuse_req *req)
 
 static void fuse_req_init_context(struct fuse_req *req)
 {
-	req->in.h.uid = current->fsuid;
-	req->in.h.gid = current->fsgid;
+	req->in.h.uid = current_fsuid();
+	req->in.h.gid = current_fsgid();
 	req->in.h.pid = current->pid;
 }
 
fs/gfs2/inode.c +5 -5
index 37725ad..6da3687 100644
@@ -692,18 +692,18 @@ static void munge_mode_uid_gid(struct gfs2_inode *dip, unsigned int *mode,
 	    (dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) {
 		if (S_ISDIR(*mode))
 			*mode |= S_ISUID;
-		else if (dip->i_inode.i_uid != current->fsuid)
+		else if (dip->i_inode.i_uid != current_fsuid())
 			*mode &= ~07111;
 		*uid = dip->i_inode.i_uid;
 	} else
-		*uid = current->fsuid;
+		*uid = current_fsuid();
 
 	if (dip->i_inode.i_mode & S_ISGID) {
 		if (S_ISDIR(*mode))
 			*mode |= S_ISGID;
 		*gid = dip->i_inode.i_gid;
 	} else
-		*gid = current->fsgid;
+		*gid = current_fsgid();
 }
 
 static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
@@ -1115,8 +1115,8 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
 		return -EPERM;
 
 	if ((dip->i_inode.i_mode & S_ISVTX) &&
-	    dip->i_inode.i_uid != current->fsuid &&
-	    ip->i_inode.i_uid != current->fsuid && !capable(CAP_FOWNER))
+	    dip->i_inode.i_uid != current_fsuid() &&
+	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
 		return -EPERM;
 
 	if (IS_APPEND(&dip->i_inode))
fs/hfs/inode.c +2 -2
index 97f8446..29caee5 100644
@@ -155,8 +155,8 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode)
 	hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name);
 	inode->i_ino = HFS_SB(sb)->next_id++;
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_nlink = 1;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	HFS_I(inode)->flags = 0;
fs/hfsplus/inode.c +2 -2
index 37744cf..af54c28 100644
@@ -312,8 +312,8 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
 
 	inode->i_ino = HFSPLUS_SB(sb).next_cnid++;
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_nlink = 1;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
fs/hpfs/namei.c +12 -12
index d256559..2af4578 100644
@@ -92,11 +92,11 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	inc_nlink(dir);
 	insert_inode_hash(result);
 
-	if (result->i_uid != current->fsuid ||
-	    result->i_gid != current->fsgid ||
+	if (result->i_uid != current_fsuid() ||
+	    result->i_gid != current_fsgid() ||
 	    result->i_mode != (mode | S_IFDIR)) {
-		result->i_uid = current->fsuid;
-		result->i_gid = current->fsgid;
+		result->i_uid = current_fsuid();
+		result->i_gid = current_fsgid();
 		result->i_mode = mode | S_IFDIR;
 		hpfs_write_inode_nolock(result);
 	}
@@ -184,11 +184,11 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, int mode, struc
 
 	insert_inode_hash(result);
 
-	if (result->i_uid != current->fsuid ||
-	    result->i_gid != current->fsgid ||
+	if (result->i_uid != current_fsuid() ||
+	    result->i_gid != current_fsgid() ||
 	    result->i_mode != (mode | S_IFREG)) {
-		result->i_uid = current->fsuid;
-		result->i_gid = current->fsgid;
+		result->i_uid = current_fsuid();
+		result->i_gid = current_fsgid();
 		result->i_mode = mode | S_IFREG;
 		hpfs_write_inode_nolock(result);
 	}
@@ -247,8 +247,8 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t
 	result->i_mtime.tv_nsec = 0;
 	result->i_atime.tv_nsec = 0;
 	hpfs_i(result)->i_ea_size = 0;
-	result->i_uid = current->fsuid;
-	result->i_gid = current->fsgid;
+	result->i_uid = current_fsuid();
+	result->i_gid = current_fsgid();
 	result->i_nlink = 1;
 	result->i_size = 0;
 	result->i_blocks = 1;
@@ -325,8 +325,8 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy
 	result->i_atime.tv_nsec = 0;
 	hpfs_i(result)->i_ea_size = 0;
 	result->i_mode = S_IFLNK | 0777;
-	result->i_uid = current->fsuid;
-	result->i_gid = current->fsgid;
+	result->i_uid = current_fsuid();
+	result->i_gid = current_fsgid();
 	result->i_blocks = 1;
 	result->i_nlink = 1;
 	result->i_size = strlen(symlink);
fs/hugetlbfs/inode.c +8 -8
index 3b3cc28..8a931bf 100644
@@ -543,9 +543,9 @@ static int hugetlbfs_mknod(struct inode *dir,
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else {
-		gid = current->fsgid;
+		gid = current_fsgid();
 	}
-	inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid, gid, mode, dev);
+	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev);
 	if (inode) {
 		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
 		d_instantiate(dentry, inode);
@@ -578,9 +578,9 @@ static int hugetlbfs_symlink(struct inode *dir,
 	if (dir->i_mode & S_ISGID)
 		gid = dir->i_gid;
 	else
-		gid = current->fsgid;
+		gid = current_fsgid();
 
-	inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid,
+	inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
 					gid, S_IFLNK|S_IRWXUGO, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
@@ -819,8 +819,8 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	config.nr_blocks = -1; /* No limit on size by default */
 	config.nr_inodes = -1; /* No limit on number of inodes by default */
-	config.uid = current->fsuid;
-	config.gid = current->fsgid;
+	config.uid = current_fsuid();
+	config.gid = current_fsgid();
 	config.mode = 0755;
 	ret = hugetlbfs_parse_options(data, &config);
 	if (ret)
@@ -933,8 +933,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size)
 		goto out_shm_unlock;
 
 	error = -ENOSPC;
-	inode = hugetlbfs_get_inode(root->d_sb, current->fsuid,
-				current->fsgid, S_IFREG | S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
+				current_fsgid(), S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
 
fs/jffs2/fs.c +2 -2
index e26ea78..b687a72 100644
@@ -433,14 +433,14 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i
 
 	memset(ri, 0, sizeof(*ri));
 	/* Set OS-specific defaults for new inodes */
-	ri->uid = cpu_to_je16(current->fsuid);
+	ri->uid = cpu_to_je16(current_fsuid());
 
 	if (dir_i->i_mode & S_ISGID) {
 		ri->gid = cpu_to_je16(dir_i->i_gid);
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else {
-		ri->gid = cpu_to_je16(current->fsgid);
+		ri->gid = cpu_to_je16(current_fsgid());
 	}
 
 	/* POSIX ACLs have to be processed now, at least partly.
fs/jfs/jfs_inode.c +2 -2
index ed6574b..70022fd 100644
@@ -93,13 +93,13 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 		return ERR_PTR(rc);
 	}
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (parent->i_mode & S_ISGID) {
 		inode->i_gid = parent->i_gid;
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 
 	/*
 	 * New inodes need to save sane values on disk when
fs/locks.c +1 -1
index 49354b9..7f82a98 100644
@@ -1355,7 +1355,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	struct inode *inode = dentry->d_inode;
 	int error, rdlease_count = 0, wrlease_count = 0;
 
-	if ((current->fsuid != inode->i_uid) && !capable(CAP_LEASE))
+	if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE))
 		return -EACCES;
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
fs/minix/bitmap.c +2 -2
index 703cc35..3aebe32 100644
@@ -262,8 +262,8 @@ struct inode * minix_new_inode(const struct inode * dir, int * error)
 		iput(inode);
 		return NULL;
 	}
-	inode->i_uid = current->fsuid;
-	inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid();
 	inode->i_ino = j;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	inode->i_blocks = 0;
fs/namei.c +4 -4
index 241cff4..21b944f 100644
@@ -184,7 +184,7 @@ int generic_permission(struct inode *inode, int mask,
 {
 	umode_t			mode = inode->i_mode;
 
-	if (current->fsuid == inode->i_uid)
+	if (current_fsuid() == inode->i_uid)
 		mode >>= 6;
 	else {
 		if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
@@ -452,7 +452,7 @@ static int exec_permission_lite(struct inode *inode,
 	if (inode->i_op && inode->i_op->permission)
 		return -EAGAIN;
 
-	if (current->fsuid == inode->i_uid)
+	if (current_fsuid() == inode->i_uid)
 		mode >>= 6;
 	else if (in_group_p(inode->i_gid))
 		mode >>= 3;
@@ -1435,9 +1435,9 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 {
 	if (!(dir->i_mode & S_ISVTX))
 		return 0;
-	if (inode->i_uid == current->fsuid)
+	if (inode->i_uid == current_fsuid())
 		return 0;
-	if (dir->i_uid == current->fsuid)
+	if (dir->i_uid == current_fsuid())
 		return 0;
 	return !capable(CAP_FOWNER);
 }
fs/nfsd/vfs.c +2 -2
index cc75e4f..727b6dd 100644
@@ -1866,7 +1866,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 		IS_APPEND(inode)?	" append" : "",
 		IS_RDONLY(inode)?	" ro" : "");
 	dprintk("      owner %d/%d user %d/%d\n",
-		inode->i_uid, inode->i_gid, current->fsuid, current->fsgid);
+		inode->i_uid, inode->i_gid, current_fsuid(), current_fsgid());
 #endif
 
 	/* Normally we reject any write/sattr etc access on a read-only file
@@ -1908,7 +1908,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 	 * with NFSv3.
 	 */
 	if ((acc & MAY_OWNER_OVERRIDE) &&
-	    inode->i_uid == current->fsuid)
+	    inode->i_uid == current_fsuid())
 		return 0;
 
 	err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL);
fs/ocfs2/dlm/dlmfs.c +4 -4
index 61a000f..5436ea3 100644
@@ -340,8 +340,8 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 		ip = DLMFS_I(inode);
 
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -366,8 +366,8 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 		return NULL;
 
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_blocks = 0;
 	inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
fs/ocfs2/namei.c +2 -2
index ae9ad95..2c5227f 100644
@@ -425,13 +425,13 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	fe->i_blkno = cpu_to_le64(fe_blkno);
 	fe->i_suballoc_bit = cpu_to_le16(suballoc_bit);
 	fe->i_suballoc_slot = cpu_to_le16(osb->slot_num);
-	fe->i_uid = cpu_to_le32(current->fsuid);
+	fe->i_uid = cpu_to_le32(current_fsuid());
 	if (dir->i_mode & S_ISGID) {
 		fe->i_gid = cpu_to_le32(dir->i_gid);
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		fe->i_gid = cpu_to_le32(current->fsgid);
+		fe->i_gid = cpu_to_le32(current_fsgid());
 	fe->i_mode = cpu_to_le16(mode);
 	if (S_ISCHR(mode) || S_ISBLK(mode))
 		fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev));
fs/pipe.c +2 -2
index e66ec48..598cf6c 100644
@@ -938,8 +938,8 @@ static struct inode * get_pipe_inode(void)
 	 */
 	inode->i_state = I_DIRTY;
 	inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
 	return inode;
fs/posix_acl.c +2 -2
index aec931e..39df95a 100644
@@ -217,11 +217,11 @@ posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want)
                 switch(pa->e_tag) {
                         case ACL_USER_OBJ:
 				/* (May have been checked already) */
-                                if (inode->i_uid == current->fsuid)
+				if (inode->i_uid == current_fsuid())
                                         goto check_perm;
                                 break;
                         case ACL_USER:
-                                if (pa->e_id == current->fsuid)
+				if (pa->e_id == current_fsuid())
                                         goto mask;
 				break;
                         case ACL_GROUP_OBJ:
fs/ramfs/inode.c +2 -2
index 8428d5b..98421f7 100644
@@ -55,8 +55,8 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
 
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_mapping->a_ops = &ramfs_aops;
 		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
fs/reiserfs/namei.c +2 -2
index b378eea..84458f3 100644
@@ -582,7 +582,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, int mode)
 	/* the quota init calls have to know who to charge the quota to, so
 	 ** we have to set uid and gid here
 	 */
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	inode->i_mode = mode;
 	/* Make inode invalid - just in case we are going to drop it before
 	 * the initialization happens */
@@ -593,7 +593,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, int mode)
 		if (S_ISDIR(mode))
 			inode->i_mode |= S_ISGID;
 	} else {
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	}
 	DQUOT_INIT(inode);
 	return 0;
fs/sysv/ialloc.c +2 -2
index 115ab0d..241e976 100644
@@ -165,9 +165,9 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode)
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	inode->i_ino = fs16_to_cpu(sbi, ino);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	inode->i_blocks = 0;
fs/udf/ialloc.c +2 -2
index 636d8f6..1f3c01a 100644
@@ -105,13 +105,13 @@ struct inode *udf_new_inode(struct inode *dir, int mode, int *err)
 		mark_buffer_dirty(UDF_SB_LVIDBH(sb));
 	}
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (dir->i_mode & S_ISGID) {
 		inode->i_gid = dir->i_gid;
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else {
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 	}
 
 	UDF_I_LOCATION(inode).logicalBlockNum = block;
fs/udf/namei.c +1 -1
index bec96a6..e2d466c 100644
@@ -636,7 +636,7 @@ static int udf_mknod(struct inode *dir, struct dentry *dentry, int mode,
 	if (!inode)
 		goto out;
 
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	init_special_inode(inode, mode, rdev);
 	if (!(fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err))) {
 		inode->i_nlink--;
fs/ufs/ialloc.c +2 -2
index 7e260bc..88f8889 100644
@@ -304,13 +304,13 @@ cg_found:
 
 	inode->i_ino = cg * uspi->s_ipg + bit;
 	inode->i_mode = mode;
-	inode->i_uid = current->fsuid;
+	inode->i_uid = current_fsuid();
 	if (dir->i_mode & S_ISGID) {
 		inode->i_gid = dir->i_gid;
 		if (S_ISDIR(mode))
 			inode->i_mode |= S_ISGID;
 	} else
-		inode->i_gid = current->fsgid;
+		inode->i_gid = current_fsgid();
 
 	inode->i_blocks = 0;
 	inode->i_generation = 0;
fs/xfs/linux-2.6/xfs_linux.h +2 -2
index 3ca39c4..13e7614 100644
@@ -126,8 +126,8 @@
 
 #define current_cpu()		(raw_smp_processor_id())
 #define current_pid()		(current->pid)
-#define current_fsuid(cred)	(current->fsuid)
-#define current_fsgid(cred)	(current->fsgid)
+#define this_fsuid(cred)	(current_fsuid())
+#define this_fsgid(cred)	(current_fsgid())
 #define current_test_flags(f)	(current->flags & (f))
 #define current_set_flags_nested(sp, f)		\
 		(*(sp) = current->flags, current->flags |= (f))
fs/xfs/xfs_acl.c +3 -3
index 7272fe3..4304fbb 100644
@@ -386,7 +386,7 @@ xfs_acl_allow_set(
 	error = xfs_getattr(ip, &va, 0);
 	if (error)
 		return error;
-	if (va.va_uid != current->fsuid && !capable(CAP_FOWNER))
+	if (va.va_uid != current_fsuid() && !capable(CAP_FOWNER))
 		return EPERM;
 	return error;
 }
@@ -433,13 +433,13 @@ xfs_acl_access(
 		switch (fap->acl_entry[i].ae_tag) {
 		case ACL_USER_OBJ:
 			seen_userobj = 1;
-			if (fuid != current->fsuid)
+			if (fuid != current_fsuid())
 				continue;
 			matched.ae_tag = ACL_USER_OBJ;
 			matched.ae_perm = allows;
 			break;
 		case ACL_USER:
-			if (fap->acl_entry[i].ae_id != current->fsuid)
+			if (fap->acl_entry[i].ae_id != current_fsuid())
 				continue;
 			matched.ae_tag = ACL_USER;
 			matched.ae_perm = allows;
fs/xfs/xfs_attr.c +1 -1
index e58f321..80eb663 100644
@@ -2627,7 +2627,7 @@ attr_user_capable(
 	    !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
-	    (current_fsuid(cred) != inode->i_uid) && !capable(CAP_FOWNER))
+	    (this_fsuid(cred) != inode->i_uid) && !capable(CAP_FOWNER))
 		return -EPERM;
 	return 0;
 }
fs/xfs/xfs_inode.c +2 -2
index a550546..c6cd8e1 100644
@@ -1136,8 +1136,8 @@ xfs_ialloc(
 	ip->i_d.di_onlink = 0;
 	ip->i_d.di_nlink = nlink;
 	ASSERT(ip->i_d.di_nlink == nlink);
-	ip->i_d.di_uid = current_fsuid(cr);
-	ip->i_d.di_gid = current_fsgid(cr);
+	ip->i_d.di_uid = this_fsuid(cr);
+	ip->i_d.di_gid = this_fsgid(cr);
 	ip->i_d.di_projid = prid;
 	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 
fs/xfs/xfs_vnodeops.c +4 -4
index 5130524..0d6bb70 100644
@@ -341,7 +341,7 @@ xfs_setattr(
 	xfs_ilock(ip, lock_flags);
 
 	/* boolean: are we the file owner? */
-	file_owner = (current_fsuid(credp) == ip->i_d.di_uid);
+	file_owner = (this_fsuid(credp) == ip->i_d.di_uid);
 
 	/*
 	 * Change various properties of a file.
@@ -1846,7 +1846,7 @@ xfs_create(
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
 	error = XFS_QM_DQVOPALLOC(mp, dp,
-			current_fsuid(credp), current_fsgid(credp), prid,
+			this_fsuid(credp), this_fsgid(credp), prid,
 			XFS_QMOPT_QUOTALL|XFS_QMOPT_INHERIT, &udqp, &gdqp);
 	if (error)
 		goto std_return;
@@ -2723,7 +2723,7 @@ xfs_mkdir(
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
 	error = XFS_QM_DQVOPALLOC(mp, dp,
-			current_fsuid(credp), current_fsgid(credp), prid,
+			this_fsuid(credp), this_fsgid(credp), prid,
 			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
 	if (error)
 		goto std_return;
@@ -3214,7 +3214,7 @@ xfs_symlink(
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
 	error = XFS_QM_DQVOPALLOC(mp, dp,
-			current_fsuid(credp), current_fsgid(credp), prid,
+			this_fsuid(credp), this_fsgid(credp), prid,
 			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
 	if (error)
 		goto std_return;
include/linux/fs.h +1 -1
index 36b7abe..feea65d 100644
@@ -1059,7 +1059,7 @@ enum {
 #define has_fs_excl() atomic_read(&current->fs_excl)
 
 #define is_owner_or_cap(inode)	\
-	((current->fsuid == (inode)->i_uid) || capable(CAP_FOWNER))
+	((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
 
 /* not quite ready to be deprecated, but... */
 extern void lock_super(struct super_block *);
include/linux/sched.h +3 -0
index 8a4812c..fee9b56 100644
@@ -1264,6 +1264,9 @@ struct task_struct {
 #endif
 };
 
+#define current_fsuid() (current->fsuid)
+#define current_fsgid() (current->fsgid)
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
ipc/mqueue.c +2 -2
index 6ca7b97..590045a 100644
@@ -109,8 +109,8 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode,
 	inode = new_inode(sb);
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_mtime = inode->i_ctime = inode->i_atime =
 				CURRENT_TIME;
kernel/cgroup.c +2 -2
index 4766bb6..87c5f1e 100644
@@ -577,8 +577,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
mm/shmem.c +4 -4
index 85bed94..d96047a 100644
@@ -1499,8 +1499,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 	inode = new_inode(sb);
 	if (inode) {
 		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
+		inode->i_uid = current_fsuid();
+		inode->i_gid = current_fsgid();
 		inode->i_blocks = 0;
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
@@ -2225,8 +2225,8 @@ static int shmem_fill_super(struct super_block *sb,
 	struct inode *inode;
 	struct dentry *root;
 	int mode   = S_IRWXUGO | S_ISVTX;
-	uid_t uid = current->fsuid;
-	gid_t gid = current->fsgid;
+	uid_t uid = current_fsuid();
+	gid_t gid = current_fsgid();
 	int err = -ENOMEM;
 	struct shmem_sb_info *sbinfo;
 	unsigned long blocks = 0;
net/9p/client.c +1 -1
index 84e087e..ed5cd85 100644
@@ -1033,7 +1033,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	fid->rdir_fpos = 0;
 	fid->rdir_pos = 0;
 	fid->rdir_fcall = NULL;
-	fid->uid = current->fsuid;
+	fid->uid = current_fsuid();
 	fid->clnt = clnt;
 	fid->aux = NULL;
 
net/socket.c +2 -2
index 7651de0..56b4007 100644
@@ -488,8 +488,8 @@ static struct socket *sock_alloc(void)
 	sock = SOCKET_I(inode);
 
 	inode->i_mode = S_IFSOCK | S_IRWXUGO;
-	inode->i_uid = current->fsuid;
-	inode->i_gid = current->fsgid;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
 
 	get_cpu_var(sockets_in_use)++;
 	put_cpu_var(sockets_in_use);
net/sunrpc/auth.c +4 -4
index eca941c..83e60f8 100644
@@ -343,8 +343,8 @@ struct rpc_cred *
 rpcauth_lookupcred(struct rpc_auth *auth, int flags)
 {
 	struct auth_cred acred = {
-		.uid = current->fsuid,
-		.gid = current->fsgid,
+		.uid = current_fsuid(),
+		.gid = current_fsgid(),
 		.group_info = current->group_info,
 	};
 	struct rpc_cred *ret;
@@ -380,8 +380,8 @@ rpcauth_bindcred(struct rpc_task *task)
 {
 	struct rpc_auth *auth = task->tk_client->cl_auth;
 	struct auth_cred acred = {
-		.uid = current->fsuid,
-		.gid = current->fsgid,
+		.uid = current_fsuid(),
+		.gid = current_fsgid(),
 		.group_info = current->group_info,
 	};
 	struct rpc_cred *ret;
security/commoncap.c +2 -2
index 5aba826..c340f53 100644
@@ -484,12 +484,12 @@ int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid,
 			 */
 
 			if (!issecure (SECURE_NO_SETUID_FIXUP)) {
-				if (old_fsuid == 0 && current->fsuid != 0) {
+				if (old_fsuid == 0 && current_fsuid() != 0) {
 					current->cap_effective =
 						cap_drop_fs_set(
 						    current->cap_effective);
 				}
-				if (old_fsuid != 0 && current->fsuid == 0) {
+				if (old_fsuid != 0 && current_fsuid() == 0) {
 					current->cap_effective =
 						cap_raise_fs_set(
 						    current->cap_effective,
security/keys/key.c +1 -1
index 654d23b..4d1a253 100644
@@ -817,7 +817,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		perm |= KEY_USR_WRITE;
 
 	/* allocate a new key */
-	key = key_alloc(ktype, description, current->fsuid, current->fsgid,
+	key = key_alloc(ktype, description, current_fsuid(), current_fsgid(),
 			current, perm, flags);
 	if (IS_ERR(key)) {
 		key_ref = ERR_CAST(key);
security/keys/keyctl.c +1 -1
index 56e963b..b3a63dd 100644
@@ -810,7 +810,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm)
 	down_write(&key->sem);
 
 	/* if we're not the sysadmin, we can only change a key that we own */
-	if (capable(CAP_SYS_ADMIN) || key->uid == current->fsuid) {
+	if (capable(CAP_SYS_ADMIN) || key->uid == current_fsuid()) {
 		key->perm = perm;
 		ret = 0;
 	}
security/keys/request_key.c +5 -5
index a3f94c6..21efac2 100644
@@ -76,7 +76,7 @@ static int call_sbin_request_key(struct key_construction *cons,
 	/* allocate a new session keyring */
 	sprintf(desc, "_req.%u", key->serial);
 
-	keyring = keyring_alloc(desc, current->fsuid, current->fsgid, current,
+	keyring = keyring_alloc(desc, current_fsuid(), current_fsgid(), current,
 				KEY_ALLOC_QUOTA_OVERRUN, NULL);
 	if (IS_ERR(keyring)) {
 		ret = PTR_ERR(keyring);
@@ -89,8 +89,8 @@ static int call_sbin_request_key(struct key_construction *cons,
 		goto error_link;
 
 	/* record the UID and GID */
-	sprintf(uid_str, "%d", current->fsuid);
-	sprintf(gid_str, "%d", current->fsgid);
+	sprintf(uid_str, "%d", current_fsuid());
+	sprintf(gid_str, "%d", current_fsgid());
 
 	/* we say which key is under construction */
 	sprintf(key_str, "%d", key->serial);
@@ -278,7 +278,7 @@ static int construct_alloc_key(struct key_type *type,
 	mutex_lock(&user->cons_lock);
 
 	key = key_alloc(type, description,
-			current->fsuid, current->fsgid, current, KEY_POS_ALL,
+			current_fsuid(), current_fsgid(), current, KEY_POS_ALL,
 			flags);
 	if (IS_ERR(key))
 		goto alloc_failed;
@@ -341,7 +341,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 	struct key *key;
 	int ret;
 
-	user = key_user_lookup(current->fsuid);
+	user = key_user_lookup(current_fsuid());
 	if (!user)
 		return ERR_PTR(-ENOMEM);
 
security/keys/request_key_auth.c +1 -1
index c615d47..980d8cb 100644
@@ -194,7 +194,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info,
 	sprintf(desc, "%x", target->serial);
 
 	authkey = key_alloc(&key_type_request_key_auth, desc,
-			    current->fsuid, current->fsgid, current,
+			    current_fsuid(), current_fsgid(), current,
 			    KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH |
 			    KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(authkey)) {
author maintainer
#7 lore raw

PATCH 6/37 Security: Separate task security context from task_struct

In reply to David Howells

Separate the task security context from task_struct. At this point, the security data is temporarily embedded in the task_struct with two pointers pointing to it.

Alpha needs further alteration as it refers to UID & GID in entry.S via asm offsets.

Sparc needs further alteration as it refers to UID & GID in sclow.S via asm offsets.

---

 arch/parisc/kernel/signal.c       |    2 
 arch/powerpc/mm/fault.c           |    2 
 arch/s390/hypfs/inode.c           |    4 -
 arch/s390/kernel/compat_linux.c   |   28 ++--
 arch/sparc64/kernel/sys_sparc32.c |   28 ++--
 drivers/block/loop.c              |    5 -
 drivers/char/drm/drm_fops.c       |    2 
 drivers/char/tty_audit.c          |    5 -
 drivers/connector/cn_proc.c       |    8 +
 drivers/media/video/cpia.c        |    2 
 drivers/net/tun.c                 |    4 -
 drivers/net/wan/sbni.c            |    8 +
 drivers/usb/core/devio.c          |    8 +
 fs/affs/super.c                   |    4 -
 fs/autofs/inode.c                 |    4 -
 fs/autofs4/inode.c                |    4 -
 fs/autofs4/waitq.c                |    4 -
 fs/binfmt_elf.c                   |   12 +-
 fs/binfmt_elf_fdpic.c             |   12 +-
 fs/cifs/connect.c                 |    5 -
 fs/cifs/ioctl.c                   |    2 
 fs/dquot.c                        |    3 
 fs/ecryptfs/messaging.c           |   15 +-
 fs/exec.c                         |   20 +--
 fs/fat/inode.c                    |    4 -
 fs/fcntl.c                        |    7 +
 fs/file_table.c                   |    4 -
 fs/fuse/dir.c                     |   12 +-
 fs/hfs/super.c                    |    4 -
 fs/hfsplus/options.c              |    4 -
 fs/hpfs/super.c                   |    4 -
 fs/hugetlbfs/inode.c              |    4 -
 fs/inotify_user.c                 |    2 
 fs/ioprio.c                       |   12 +-
 fs/namei.c                        |    6 +
 fs/ncpfs/ioctl.c                  |   32 ++--
 fs/nfsd/auth.c                    |   22 ++-
 fs/nfsd/nfs4recover.c             |   12 +-
 fs/open.c                         |   22 +--
 fs/proc/array.c                   |   16 +-
 fs/proc/base.c                    |   16 +-
 fs/proc/proc_sysctl.c             |    4 -
 fs/quota.c                        |    4 -
 fs/smbfs/dir.c                    |    4 -
 fs/smbfs/inode.c                  |    2 
 fs/smbfs/proc.c                   |    2 
 include/linux/init_task.h         |   25 ++-
 include/linux/sched.h             |   80 ++++++++---
 include/net/scm.h                 |    4 -
 ipc/mqueue.c                      |    4 -
 ipc/msg.c                         |    4 -
 ipc/sem.c                         |    4 -
 ipc/shm.c                         |   16 +-
 ipc/util.c                        |    7 +
 kernel/acct.c                     |    8 +
 kernel/auditsc.c                  |   46 +++---
 kernel/cgroup.c                   |    5 -
 kernel/exit.c                     |   12 +-
 kernel/fork.c                     |   24 ++-
 kernel/futex.c                    |    8 +
 kernel/futex_compat.c             |    5 -
 kernel/ptrace.c                   |   14 +-
 kernel/sched.c                    |   11 +
 kernel/signal.c                   |   26 ++-
 kernel/sys.c                      |  278 +++++++++++++++++++++----------------
 kernel/sysctl.c                   |    2 
 kernel/timer.c                    |    8 +
 kernel/tsacct.c                   |    4 -
 kernel/uid16.c                    |   28 ++--
 kernel/user.c                     |    4 -
 kernel/user_namespace.c           |    2 
 mm/mempolicy.c                    |    7 +
 mm/migrate.c                      |    7 +
 mm/oom_kill.c                     |    2 
 net/ax25/af_ax25.c                |    2 
 net/ax25/ax25_route.c             |    2 
 net/core/dev.c                    |    2 
 net/core/scm.c                    |   10 +
 net/ipv6/ip6_flowlabel.c          |    2 
 net/netrom/af_netrom.c            |    4 -
 net/rose/af_rose.c                |    4 -
 net/sunrpc/auth.c                 |    4 -
 net/unix/af_unix.c                |   12 +-
 security/commoncap.c              |  125 +++++++++--------
 security/dummy.c                  |   40 +++--
 security/keys/keyctl.c            |   25 ++-
 security/keys/permission.c        |   11 +
 security/keys/process_keys.c      |   76 +++++-----
 security/keys/request_key.c       |   13 +-
 security/keys/request_key_auth.c  |   12 +-
 security/selinux/exports.c        |    4 -
 security/selinux/hooks.c          |  111 +++++++--------
 security/selinux/selinuxfs.c      |    2 
 security/selinux/xfrm.c           |    6 -
 94 files changed, 828 insertions(+), 674 deletions(-)
arch/parisc/kernel/signal.c +1 -1
index 58fccc9..6639d9b 100644
@@ -182,7 +182,7 @@ give_sigsegv:
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
 	si.si_pid = task_pid_vnr(current);
-	si.si_uid = current->uid;
+	si.si_uid = current->act_as->uid;
 	si.si_addr = &frame->uc;
 	force_sig_info(SIGSEGV, &si, current);
 	return;
arch/powerpc/mm/fault.c +1 -1
index 7b25107..fea0e5a 100644
@@ -363,7 +363,7 @@ bad_area_nosemaphore:
 	    && printk_ratelimit())
 		printk(KERN_CRIT "kernel tried to execute NX-protected"
 		       " page (%lx) - exploit attempt? (uid: %d)\n",
-		       address, current->uid);
+		       address, current->act_as->uid);
 
 	return SIGSEGV;
 
arch/s390/hypfs/inode.c +2 -2
index 4b010ff..56b7df6 100644
@@ -289,8 +289,8 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sbi)
 		return -ENOMEM;
 	mutex_init(&sbi->lock);
-	sbi->uid = current->uid;
-	sbi->gid = current->gid;
+	sbi->uid = current->act_as->uid;
+	sbi->gid = current->act_as->gid;
 	sb->s_fs_info = sbi;
 	sb->s_blocksize = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
arch/s390/kernel/compat_linux.c +14 -14
index 50b85d0..d939699 100644
@@ -149,9 +149,9 @@ asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
-	    !(retval = put_user(high2lowuid(current->euid), euid)))
-		retval = put_user(high2lowuid(current->suid), suid);
+	if (!(retval = put_user(high2lowuid(current->sec->uid), ruid)) &&
+	    !(retval = put_user(high2lowuid(current->sec->euid), euid)))
+		retval = put_user(high2lowuid(current->sec->suid), suid);
 
 	return retval;
 }
@@ -166,9 +166,9 @@ asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
-	    !(retval = put_user(high2lowgid(current->egid), egid)))
-		retval = put_user(high2lowgid(current->sgid), sgid);
+	if (!(retval = put_user(high2lowgid(current->sec->gid), rgid)) &&
+	    !(retval = put_user(high2lowgid(current->sec->egid), egid)))
+		retval = put_user(high2lowgid(current->sec->sgid), sgid);
 
 	return retval;
 }
@@ -218,20 +218,20 @@ asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	get_group_info(current->sec->group_info);
+	i = current->sec->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, current->sec->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
+	put_group_info(current->sec->group_info);
 	return i;
 }
 
@@ -262,22 +262,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 
 asmlinkage long sys32_getuid16(void)
 {
-	return high2lowuid(current->uid);
+	return high2lowuid(current->sec->uid);
 }
 
 asmlinkage long sys32_geteuid16(void)
 {
-	return high2lowuid(current->euid);
+	return high2lowuid(current->sec->euid);
 }
 
 asmlinkage long sys32_getgid16(void)
 {
-	return high2lowgid(current->gid);
+	return high2lowgid(current->sec->gid);
 }
 
 asmlinkage long sys32_getegid16(void)
 {
-	return high2lowgid(current->egid);
+	return high2lowgid(current->sec->egid);
 }
 
 /* 32-bit timeval and related flotsam.  */
arch/sparc64/kernel/sys_sparc32.c +14 -14
index 98c4688..28ddfb5 100644
@@ -105,9 +105,9 @@ asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
-	    !(retval = put_user(high2lowuid(current->euid), euid)))
-		retval = put_user(high2lowuid(current->suid), suid);
+	if (!(retval = put_user(high2lowuid(current->sec->uid), ruid)) &&
+	    !(retval = put_user(high2lowuid(current->sec->euid), euid)))
+		retval = put_user(high2lowuid(current->sec->suid), suid);
 
 	return retval;
 }
@@ -122,9 +122,9 @@ asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
-	    !(retval = put_user(high2lowgid(current->egid), egid)))
-		retval = put_user(high2lowgid(current->sgid), sgid);
+	if (!(retval = put_user(high2lowgid(current->sec->gid), rgid)) &&
+	    !(retval = put_user(high2lowgid(current->sec->egid), egid)))
+		retval = put_user(high2lowgid(current->sec->sgid), sgid);
 
 	return retval;
 }
@@ -174,20 +174,20 @@ asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	get_group_info(current->sec->group_info);
+	i = current->sec->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, current->sec->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
+	put_group_info(current->sec->group_info);
 	return i;
 }
 
@@ -218,22 +218,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 
 asmlinkage long sys32_getuid16(void)
 {
-	return high2lowuid(current->uid);
+	return high2lowuid(current->sec->uid);
 }
 
 asmlinkage long sys32_geteuid16(void)
 {
-	return high2lowuid(current->euid);
+	return high2lowuid(current->sec->euid);
 }
 
 asmlinkage long sys32_getgid16(void)
 {
-	return high2lowgid(current->gid);
+	return high2lowgid(current->sec->gid);
 }
 
 asmlinkage long sys32_getegid16(void)
 {
-	return high2lowgid(current->egid);
+	return high2lowgid(current->sec->egid);
 }
 
 /* 32-bit timeval and related flotsam.  */
drivers/block/loop.c +3 -2
index 91ebb00..fc5caaf 100644
@@ -928,7 +928,8 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	struct loop_func_table *xfer;
 
-	if (lo->lo_encrypt_key_size && lo->lo_key_owner != current->uid &&
+	if (lo->lo_encrypt_key_size &&
+	    lo->lo_key_owner != current->act_as->uid &&
 	    !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (lo->lo_state != Lo_bound)
@@ -983,7 +984,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (info->lo_encrypt_key_size) {
 		memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
 		       info->lo_encrypt_key_size);
-		lo->lo_key_owner = current->uid;
+		lo->lo_key_owner = current->act_as->uid;
 	}	
 
 	return 0;
drivers/char/drm/drm_fops.c +1 -1
index 3992f73..1f8d0a7 100644
@@ -243,7 +243,7 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 	memset(priv, 0, sizeof(*priv));
 	filp->private_data = priv;
 	priv->filp = filp;
-	priv->uid = current->euid;
+	priv->uid = current->act_as->euid;
 	priv->pid = task_pid_nr(current);
 	priv->minor = minor;
 	priv->head = drm_heads[minor];
drivers/char/tty_audit.c +3 -2
index bacded0..58d4639 100644
@@ -87,8 +87,9 @@ static void tty_audit_buf_push(struct task_struct *tsk, uid_t loginuid,
 		char name[sizeof(tsk->comm)];
 
 		audit_log_format(ab, "tty pid=%u uid=%u auid=%u ses=%u "
-				 "major=%d minor=%d comm=", tsk->pid, tsk->uid,
-				 loginuid, sessionid, buf->major, buf->minor);
+				 "major=%d minor=%d comm=",
+				 tsk->pid, tsk->sec->uid, loginuid, sessionid,
+				 buf->major, buf->minor);
 		get_task_comm(name, tsk);
 		audit_log_untrustedstring(ab, name);
 		audit_log_format(ab, " data=");
drivers/connector/cn_proc.c +4 -4
index 5c9f67f..5a004dd 100644
@@ -116,11 +116,11 @@ void proc_id_connector(struct task_struct *task, int which_id)
 	ev->event_data.id.process_pid = task->pid;
 	ev->event_data.id.process_tgid = task->tgid;
 	if (which_id == PROC_EVENT_UID) {
-	 	ev->event_data.id.r.ruid = task->uid;
-	 	ev->event_data.id.e.euid = task->euid;
+		ev->event_data.id.r.ruid = task->act_as->uid;
+		ev->event_data.id.e.euid = task->act_as->euid;
 	} else if (which_id == PROC_EVENT_GID) {
-	   	ev->event_data.id.r.rgid = task->gid;
-	   	ev->event_data.id.e.egid = task->egid;
+		ev->event_data.id.r.rgid = task->act_as->gid;
+		ev->event_data.id.e.egid = task->act_as->egid;
 	} else
 	     	return;
 	get_seq(&msg->seq, &ev->cpu);
drivers/media/video/cpia.c +1 -1
index 7c630f5..5b178ab 100644
@@ -3202,7 +3202,7 @@ static int cpia_open(struct inode *inode, struct file *file)
 
 	/* Set ownership of /proc/cpia/videoX to current user */
 	if(cam->proc_entry)
-		cam->proc_entry->uid = current->uid;
+		cam->proc_entry->uid = current->act_as->uid;
 
 	/* set mark for loading first frame uncompressed */
 	cam->first_frame = 1;
drivers/net/tun.c +2 -2
index 038c1ef..2b63957 100644
@@ -463,9 +463,9 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr)
 
 		/* Check permissions */
 		if (((tun->owner != -1 &&
-		      current->euid != tun->owner) ||
+		      current->act_as->euid != tun->owner) ||
 		     (tun->group != -1 &&
-		      current->egid != tun->group)) &&
+		      current->act_as->egid != tun->group)) &&
 		     !capable(CAP_NET_ADMIN))
 			return -EPERM;
 	}
drivers/net/wan/sbni.c +4 -4
index 15d5c58..1b054c5 100644
@@ -1317,7 +1317,7 @@ sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
 		break;
 
 	case  SIOCDEVRESINSTATS :
-		if( current->euid != 0 )	/* root only */
+		if (current->act_as->euid != 0)	/* root only */
 			return  -EPERM;
 		memset( &nl->in_stats, 0, sizeof(struct sbni_in_stats) );
 		break;
@@ -1334,7 +1334,7 @@ sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
 		break;
 
 	case  SIOCDEVSHWSTATE :
-		if( current->euid != 0 )	/* root only */
+		if (current->act_as->euid != 0)	/* root only */
 			return  -EPERM;
 
 		spin_lock( &nl->lock );
@@ -1355,7 +1355,7 @@ sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
 #ifdef CONFIG_SBNI_MULTILINE
 
 	case  SIOCDEVENSLAVE :
-		if( current->euid != 0 )	/* root only */
+		if (current->act_as->euid != 0)	/* root only */
 			return  -EPERM;
 
 		if (copy_from_user( slave_name, ifr->ifr_data, sizeof slave_name ))
@@ -1370,7 +1370,7 @@ sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
 		return  enslave( dev, slave_dev );
 
 	case  SIOCDEVEMANSIPATE :
-		if( current->euid != 0 )	/* root only */
+		if (current->act_as->euid != 0)	/* root only */
 			return  -EPERM;
 
 		return  emancipate( dev );
drivers/usb/core/devio.c +4 -4
index ae94176..1b0f54a 100644
@@ -599,8 +599,8 @@ static int usbdev_open(struct inode *inode, struct file *file)
 	init_waitqueue_head(&ps->wait);
 	ps->discsignr = 0;
 	ps->disc_pid = get_pid(task_pid(current));
-	ps->disc_uid = current->uid;
-	ps->disc_euid = current->euid;
+	ps->disc_uid = current->sec->uid;
+	ps->disc_euid = current->sec->euid;
 	ps->disccontext = NULL;
 	ps->ifclaimed = 0;
 	security_task_getsecid(current, &ps->secid);
@@ -1130,8 +1130,8 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
 	as->signr = uurb->signr;
 	as->ifnum = ifnum;
 	as->pid = get_pid(task_pid(current));
-	as->uid = current->uid;
-	as->euid = current->euid;
+	as->uid = current->sec->uid;
+	as->euid = current->sec->euid;
 	security_task_getsecid(current, &as->secid);
 	if (!is_in) {
 		if (copy_from_user(as->urb->transfer_buffer, uurb->buffer,
fs/affs/super.c +2 -2
index 3c45d49..902e4e9 100644
@@ -158,8 +158,8 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 
 	/* Fill in defaults */
 
-	*uid        = current->uid;
-	*gid        = current->gid;
+	*uid        = current->sec->uid;
+	*gid        = current->sec->gid;
 	*reserved   = 2;
 	*root       = -1;
 	*blocksize  = -1;
fs/autofs/inode.c +2 -2
index 708bdb8..c1063de 100644
@@ -75,8 +75,8 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
 	substring_t args[MAX_OPT_ARGS];
 	int option;
 
-	*uid = current->uid;
-	*gid = current->gid;
+	*uid = current->sec->uid;
+	*gid = current->sec->gid;
 	*pgrp = task_pgrp_nr(current);
 
 	*minproto = *maxproto = AUTOFS_PROTO_VERSION;
fs/autofs4/inode.c +2 -2
index 7f05d6c..fac6121 100644
@@ -224,8 +224,8 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
 	substring_t args[MAX_OPT_ARGS];
 	int option;
 
-	*uid = current->uid;
-	*gid = current->gid;
+	*uid = current->sec->uid;
+	*gid = current->sec->gid;
 	*pgrp = task_pgrp_nr(current);
 
 	*minproto = AUTOFS_MIN_PROTO_VERSION;
fs/autofs4/waitq.c +2 -2
index 1fe28e4..f41f5b7 100644
@@ -294,8 +294,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		wq->len = len;
 		wq->dev = autofs4_get_dev(sbi);
 		wq->ino = autofs4_get_ino(sbi);
-		wq->uid = current->uid;
-		wq->gid = current->gid;
+		wq->uid = current->sec->uid;
+		wq->gid = current->sec->gid;
 		wq->pid = current->pid;
 		wq->tgid = current->tgid;
 		wq->status = -EINTR; /* Status return if interrupted */
fs/binfmt_elf.c +6 -6
index 111771d..fed9bc6 100644
@@ -201,10 +201,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	NEW_AUX_ENT(AT_BASE, interp_load_addr);
 	NEW_AUX_ENT(AT_FLAGS, 0);
 	NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
-	NEW_AUX_ENT(AT_UID, tsk->uid);
-	NEW_AUX_ENT(AT_EUID, tsk->euid);
-	NEW_AUX_ENT(AT_GID, tsk->gid);
-	NEW_AUX_ENT(AT_EGID, tsk->egid);
+	NEW_AUX_ENT(AT_UID, tsk->sec->uid);
+	NEW_AUX_ENT(AT_EUID, tsk->sec->euid);
+	NEW_AUX_ENT(AT_GID, tsk->sec->gid);
+	NEW_AUX_ENT(AT_EGID, tsk->sec->egid);
  	NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
 	if (k_platform) {
 		NEW_AUX_ENT(AT_PLATFORM,
@@ -1502,8 +1502,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_zomb = psinfo->pr_sname == 'Z';
 	psinfo->pr_nice = task_nice(p);
 	psinfo->pr_flag = p->flags;
-	SET_UID(psinfo->pr_uid, p->uid);
-	SET_GID(psinfo->pr_gid, p->gid);
+	SET_UID(psinfo->pr_uid, p->sec->uid);
+	SET_GID(psinfo->pr_gid, p->sec->gid);
 	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
 	
 	return 0;
fs/binfmt_elf_fdpic.c +6 -6
index 32649f2..0ebb7eb 100644
@@ -585,10 +585,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	NEW_AUX_ENT( 6,	AT_BASE,	interp_params->elfhdr_addr);
 	NEW_AUX_ENT( 7, AT_FLAGS,	0);
 	NEW_AUX_ENT( 8, AT_ENTRY,	exec_params->entry_addr);
-	NEW_AUX_ENT( 9, AT_UID,		(elf_addr_t) current->uid);
-	NEW_AUX_ENT(10, AT_EUID,	(elf_addr_t) current->euid);
-	NEW_AUX_ENT(11, AT_GID,		(elf_addr_t) current->gid);
-	NEW_AUX_ENT(12, AT_EGID,	(elf_addr_t) current->egid);
+	NEW_AUX_ENT( 9, AT_UID,		(elf_addr_t) current->sec->uid);
+	NEW_AUX_ENT(10, AT_EUID,	(elf_addr_t) current->sec->euid);
+	NEW_AUX_ENT(11, AT_GID,		(elf_addr_t) current->sec->gid);
+	NEW_AUX_ENT(12, AT_EGID,	(elf_addr_t) current->sec->egid);
 
 #ifdef ARCH_DLINFO
 	/* ARCH_DLINFO must come last so platform specific code can enforce
@@ -1402,8 +1402,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 	psinfo->pr_zomb = psinfo->pr_sname == 'Z';
 	psinfo->pr_nice = task_nice(p);
 	psinfo->pr_flag = p->flags;
-	SET_UID(psinfo->pr_uid, p->uid);
-	SET_GID(psinfo->pr_gid, p->gid);
+	SET_UID(psinfo->pr_uid, p->sec->uid);
+	SET_GID(psinfo->pr_gid, p->sec->gid);
 	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
 
 	return 0;
fs/cifs/connect.c +3 -2
index 65d0ba7..5fcd5e0 100644
@@ -818,8 +818,9 @@ cifs_parse_mount_options(char *options, const char *devname,
 	/* null target name indicates to use *SMBSERVR default called name
 	   if we end up sending RFC1001 session initialize */
 	vol->target_rfc1001_name[0] = 0;
-	vol->linux_uid = current->uid;	/* current->euid instead? */
-	vol->linux_gid = current->gid;
+	vol->linux_uid = current->sec->uid;  /* use current->act_as->euid
+					      * instead? */
+	vol->linux_gid = current->sec->gid;
 	vol->dir_mode = S_IRWXUGO;
 	/* 2767 perms indicate mandatory locking support */
 	vol->file_mode = (S_IRWXUGO | S_ISGID) & (~S_IXGRP);
fs/cifs/ioctl.c +1 -1
index d24fe68..bf61a78 100644
@@ -65,7 +65,7 @@ int cifs_ioctl (struct inode *inode, struct file *filep,
 	switch (command) {
 		case CIFS_IOC_CHECKUMOUNT:
 			cFYI(1, ("User unmount attempted"));
-			if (cifs_sb->mnt_uid == current->uid)
+			if (cifs_sb->mnt_uid == current->sec->uid)
 				rc = 0;
 			else {
 				rc = -EACCES;
fs/dquot.c +2 -1
index bd1f666..3e36b99 100644
@@ -960,7 +960,8 @@ static void send_warning(const struct dquot *dquot, const char warntype)
 		MINOR(dquot->dq_sb->s_dev));
 	if (ret)
 		goto attr_err_out;
-	ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, current->user->uid);
+	ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID,
+			  current->act_as->user->uid);
 	if (ret)
 		goto attr_err_out;
 	genlmsg_end(skb, msg_head);
fs/ecryptfs/messaging.c +8 -7
index 9cc2aec..d035a5f 100644
@@ -264,26 +264,27 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t uid,
 	}
 	msg_ctx = &ecryptfs_msg_ctx_arr[msg->index];
 	mutex_lock(&msg_ctx->mux);
-	if (ecryptfs_find_daemon_id(msg_ctx->task->euid, &id)) {
+	if (ecryptfs_find_daemon_id(msg_ctx->task->sec->euid, &id)) {
 		rc = -EBADMSG;
 		ecryptfs_printk(KERN_WARNING, "User [%d] received a "
 				"message response from process [%d] but does "
 				"not have a registered daemon\n",
-				msg_ctx->task->euid, pid);
+				msg_ctx->task->sec->euid, pid);
 		goto wake_up;
 	}
-	if (msg_ctx->task->euid != uid) {
+	if (msg_ctx->task->sec->euid != uid) {
 		rc = -EBADMSG;
 		ecryptfs_printk(KERN_WARNING, "Received message from user "
 				"[%d]; expected message from user [%d]\n",
-				uid, msg_ctx->task->euid);
+				uid, msg_ctx->task->sec->euid);
 		goto unlock;
 	}
 	if (id->pid != pid) {
 		rc = -EBADMSG;
 		ecryptfs_printk(KERN_ERR, "User [%d] received a "
 				"message response from an unrecognized "
-				"process [%d]\n", msg_ctx->task->euid, pid);
+				"process [%d]\n",
+				msg_ctx->task->sec->euid, pid);
 		goto unlock;
 	}
 	if (msg_ctx->state != ECRYPTFS_MSG_CTX_STATE_PENDING) {
@@ -331,11 +332,11 @@ int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
 	int rc;
 
 	mutex_lock(&ecryptfs_daemon_id_hash_mux);
-	if (ecryptfs_find_daemon_id(current->euid, &id)) {
+	if (ecryptfs_find_daemon_id(current->act_as->euid, &id)) {
 		mutex_unlock(&ecryptfs_daemon_id_hash_mux);
 		rc = -ENOTCONN;
 		ecryptfs_printk(KERN_ERR, "User [%d] does not have a daemon "
-				"registered\n", current->euid);
+				"registered\n", current->sec->euid);
 		goto out;
 	}
 	mutex_unlock(&ecryptfs_daemon_id_hash_mux);
fs/exec.c +11 -9
index 2516cb0..c09a2d9 100644
@@ -996,7 +996,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
-	if (current->euid == current->uid && current->egid == current->gid)
+	if (current->sec->euid == current->sec->uid &&
+	    current->sec->egid == current->sec->gid)
 		set_dumpable(current->mm, 1);
 	else
 		set_dumpable(current->mm, suid_dumpable);
@@ -1023,7 +1024,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 */
 	current->mm->task_size = TASK_SIZE;
 
-	if (bprm->e_uid != current->euid || bprm->e_gid != current->egid) {
+	if (bprm->e_uid != current->sec->euid ||
+	    bprm->e_gid != current->sec->egid) {
 		suid_keys(current);
 		set_dumpable(current->mm, suid_dumpable);
 		current->pdeath_signal = 0;
@@ -1065,8 +1067,8 @@ int prepare_binprm(struct linux_binprm *bprm)
 	if (bprm->file->f_op == NULL)
 		return -EACCES;
 
-	bprm->e_uid = current->euid;
-	bprm->e_gid = current->egid;
+	bprm->e_uid = current->sec->euid;
+	bprm->e_gid = current->sec->egid;
 
 	if(!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
 		/* Set-uid? */
@@ -1119,7 +1121,7 @@ void compute_creds(struct linux_binprm *bprm)
 {
 	int unsafe;
 
-	if (bprm->e_uid != current->uid) {
+	if (bprm->e_uid != current->sec->uid) {
 		suid_keys(current);
 		current->pdeath_signal = 0;
 	}
@@ -1437,7 +1439,7 @@ static int format_corename(char *corename, const char *pattern, long signr)
 			/* uid */
 			case 'u':
 				rc = snprintf(out_ptr, out_end - out_ptr,
-					      "%d", current->uid);
+					      "%d", current->sec->uid);
 				if (rc > out_end - out_ptr)
 					goto out;
 				out_ptr += rc;
@@ -1445,7 +1447,7 @@ static int format_corename(char *corename, const char *pattern, long signr)
 			/* gid */
 			case 'g':
 				rc = snprintf(out_ptr, out_end - out_ptr,
-					      "%d", current->gid);
+					      "%d", current->sec->gid);
 				if (rc > out_end - out_ptr)
 					goto out;
 				out_ptr += rc;
@@ -1703,7 +1705,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 	 */
 	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
-		current->fsuid = 0;	/* Dump root private */
+		current->act_as->fsuid = 0;	/* Dump root private */
 	}
 
 	retval = coredump_wait(exit_code);
@@ -1799,7 +1801,7 @@ fail_unlock:
 	if (helper_argv)
 		argv_free(helper_argv);
 
-	current->fsuid = fsuid;
+	current->act_as->fsuid = fsuid;
 	complete_all(&mm->core_done);
 fail:
 	return retval;
fs/fat/inode.c +2 -2
index 085269e..29097fb 100644
@@ -932,8 +932,8 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 
 	opts->isvfat = is_vfat;
 
-	opts->fs_uid = current->uid;
-	opts->fs_gid = current->gid;
+	opts->fs_uid = current->sec->uid;
+	opts->fs_gid = current->sec->gid;
 	opts->fs_fmask = opts->fs_dmask = current->fs->umask;
 	opts->codepage = fat_default_codepage;
 	opts->iocharset = fat_default_iocharset;
fs/fcntl.c +4 -3
index 8685263..35d8f74 100644
@@ -276,7 +276,8 @@ int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 	if (err)
 		return err;
 
-	f_modown(filp, pid, type, current->uid, current->euid, force);
+	f_modown(filp, pid, type, current->sec->uid, current->act_as->euid,
+		 force);
 	return 0;
 }
 EXPORT_SYMBOL(__f_setown);
@@ -461,8 +462,8 @@ static inline int sigio_perm(struct task_struct *p,
                              struct fown_struct *fown, int sig)
 {
 	return (((fown->euid == 0) ||
-		 (fown->euid == p->suid) || (fown->euid == p->uid) ||
-		 (fown->uid == p->suid) || (fown->uid == p->uid)) &&
+		 (fown->euid == p->sec->suid) || (fown->euid == p->sec->uid) ||
+		 (fown->uid == p->sec->suid) || (fown->uid == p->sec->uid)) &&
 		!security_file_send_sigiotask(p, fown, sig));
 }
 
fs/file_table.c +2 -2
index 664e3f2..e559b50 100644
@@ -114,8 +114,8 @@ struct file *get_empty_filp(void)
 	INIT_LIST_HEAD(&f->f_u.fu_list);
 	atomic_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
-	f->f_uid = tsk->fsuid;
-	f->f_gid = tsk->fsgid;
+	f->f_uid = tsk->act_as->fsuid;
+	f->f_gid = tsk->act_as->fsgid;
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
 	return f;
fs/fuse/dir.c +6 -6
index 7fb514b..565bfa9 100644
@@ -831,12 +831,12 @@ int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task)
 	if (fc->flags & FUSE_ALLOW_OTHER)
 		return 1;
 
-	if (task->euid == fc->user_id &&
-	    task->suid == fc->user_id &&
-	    task->uid == fc->user_id &&
-	    task->egid == fc->group_id &&
-	    task->sgid == fc->group_id &&
-	    task->gid == fc->group_id)
+	if (task->sec->euid == fc->user_id &&
+	    task->sec->suid == fc->user_id &&
+	    task->sec->uid == fc->user_id &&
+	    task->sec->egid == fc->group_id &&
+	    task->sec->sgid == fc->group_id &&
+	    task->sec->gid == fc->group_id)
 		return 1;
 
 	return 0;
fs/hfs/super.c +2 -2
index 32de44e..4c2f0c1 100644
@@ -210,8 +210,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 	int tmp, token;
 
 	/* initialize the sb with defaults */
-	hsb->s_uid = current->uid;
-	hsb->s_gid = current->gid;
+	hsb->s_uid = current->sec->uid;
+	hsb->s_gid = current->sec->gid;
 	hsb->s_file_umask = 0133;
 	hsb->s_dir_umask = 0022;
 	hsb->s_type = hsb->s_creator = cpu_to_be32(0x3f3f3f3f);	/* == '????' */
fs/hfsplus/options.c +2 -2
index dc64fac..fa5e015 100644
@@ -49,8 +49,8 @@ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts)
 	opts->creator = HFSPLUS_DEF_CR_TYPE;
 	opts->type = HFSPLUS_DEF_CR_TYPE;
 	opts->umask = current->fs->umask;
-	opts->uid = current->uid;
-	opts->gid = current->gid;
+	opts->uid = current->sec->uid;
+	opts->gid = current->sec->gid;
 	opts->part = -1;
 	opts->session = -1;
 }
fs/hpfs/super.c +2 -2
index 00971d9..cf4c6b5 100644
@@ -464,8 +464,8 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 
 	init_MUTEX(&sbi->hpfs_creation_de);
 
-	uid = current->uid;
-	gid = current->gid;
+	uid = current->sec->uid;
+	gid = current->sec->gid;
 	umask = current->fs->umask;
 	lowercase = 0;
 	conv = CONV_BINARY;
fs/hugetlbfs/inode.c +2 -2
index 8a931bf..1696891 100644
@@ -921,7 +921,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size)
 	if (!can_do_hugetlb_shm())
 		return ERR_PTR(-EPERM);
 
-	if (!user_shm_lock(size, current->user))
+	if (!user_shm_lock(size, current->sec->user))
 		return ERR_PTR(-ENOMEM);
 
 	root = hugetlbfs_vfsmount->mnt_root;
@@ -960,7 +960,7 @@ out_inode:
 out_dentry:
 	dput(dentry);
 out_shm_unlock:
-	user_shm_unlock(size, current->user);
+	user_shm_unlock(size, current->sec->user);
 	return ERR_PTR(error);
 }
 
fs/inotify_user.c +1 -1
index a336c97..f1cecf9 100644
@@ -584,7 +584,7 @@ asmlinkage long sys_inotify_init(void)
 		goto out_put_fd;
 	}
 
-	user = get_uid(current->user);
+	user = get_uid(current->sec->user);
 	if (unlikely(atomic_read(&user->inotify_devs) >=
 			inotify_max_user_instances)) {
 		ret = -EMFILE;
fs/ioprio.c +6 -6
index c4a1c3c..befcda5 100644
@@ -32,8 +32,8 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
 	int err;
 	struct io_context *ioc;
 
-	if (task->uid != current->euid &&
-	    task->uid != current->uid && !capable(CAP_SYS_NICE))
+	if (task->sec->uid != current->act_as->euid &&
+	    task->sec->uid != current->act_as->uid && !capable(CAP_SYS_NICE))
 		return -EPERM;
 
 	err = security_task_setioprio(task, ioprio);
@@ -123,7 +123,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 			break;
 		case IOPRIO_WHO_USER:
 			if (!who)
-				user = current->user;
+				user = current->sec->user;
 			else
 				user = find_user(who);
 
@@ -131,7 +131,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 				break;
 
 			do_each_thread(g, p) {
-				if (p->uid != who)
+				if (p->sec->uid != who)
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
@@ -216,7 +216,7 @@ asmlinkage long sys_ioprio_get(int which, int who)
 			break;
 		case IOPRIO_WHO_USER:
 			if (!who)
-				user = current->user;
+				user = current->sec->user;
 			else
 				user = find_user(who);
 
@@ -224,7 +224,7 @@ asmlinkage long sys_ioprio_get(int which, int who)
 				break;
 
 			do_each_thread(g, p) {
-				if (p->uid != user->uid)
+				if (p->sec->uid != user->uid)
 					continue;
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)
fs/namei.c +4 -2
index 21b944f..4db2257 100644
@@ -1433,11 +1433,13 @@ int fastcall __user_walk(const char __user *name, unsigned flags, struct nameida
  */
 static inline int check_sticky(struct inode *dir, struct inode *inode)
 {
+	uid_t fsuid = current->act_as->fsuid;
+
 	if (!(dir->i_mode & S_ISVTX))
 		return 0;
-	if (inode->i_uid == current_fsuid())
+	if (inode->i_uid == fsuid)
 		return 0;
-	if (dir->i_uid == current_fsuid())
+	if (dir->i_uid == fsuid)
 		return 0;
 	return !capable(CAP_FOWNER);
 }
fs/ncpfs/ioctl.c +16 -16
index c67b4bd..5f1adaf 100644
@@ -40,7 +40,7 @@ ncp_get_fs_info(struct ncp_server * server, struct file *file,
 	struct ncp_fs_info info;
 
 	if ((file_permission(file, MAY_WRITE) != 0)
-	    && (current->uid != server->m.mounted_uid)) {
+	    && (current->act_as->uid != server->m.mounted_uid)) {
 		return -EACCES;
 	}
 	if (copy_from_user(&info, arg, sizeof(info)))
@@ -70,7 +70,7 @@ ncp_get_fs_info_v2(struct ncp_server * server, struct file *file,
 	struct ncp_fs_info_v2 info2;
 
 	if ((file_permission(file, MAY_WRITE) != 0)
-	    && (current->uid != server->m.mounted_uid)) {
+	    && (current->act_as->uid != server->m.mounted_uid)) {
 		return -EACCES;
 	}
 	if (copy_from_user(&info2, arg, sizeof(info2)))
@@ -141,7 +141,7 @@ ncp_get_compat_fs_info_v2(struct ncp_server * server, struct file *file,
 	struct compat_ncp_fs_info_v2 info2;
 
 	if ((file_permission(file, MAY_WRITE) != 0)
-	    && (current->uid != server->m.mounted_uid)) {
+	    && (current->act_as->uid != server->m.mounted_uid)) {
 		return -EACCES;
 	}
 	if (copy_from_user(&info2, arg, sizeof(info2)))
@@ -276,7 +276,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 #endif
 	case NCP_IOC_NCPREQUEST:
 		if ((file_permission(filp, MAY_WRITE) != 0)
-		    && (current->uid != server->m.mounted_uid)) {
+		    && (current->act_as->uid != server->m.mounted_uid)) {
 			return -EACCES;
 		}
 #ifdef CONFIG_COMPAT
@@ -356,7 +356,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 	case NCP_IOC_GETMOUNTUID32:
 	case NCP_IOC_GETMOUNTUID64:
 		if ((file_permission(filp, MAY_READ) != 0)
-			&& (current->uid != server->m.mounted_uid)) {
+			&& (current->act_as->uid != server->m.mounted_uid)) {
 			return -EACCES;
 		}
 		if (cmd == NCP_IOC_GETMOUNTUID16) {
@@ -380,7 +380,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 			struct ncp_setroot_ioctl sr;
 
 			if ((file_permission(filp, MAY_READ) != 0)
-			    && (current->uid != server->m.mounted_uid))
+			    && (current->act_as->uid != server->m.mounted_uid))
 			{
 				return -EACCES;
 			}
@@ -455,7 +455,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 #ifdef CONFIG_NCPFS_PACKET_SIGNING	
 	case NCP_IOC_SIGN_INIT:
 		if ((file_permission(filp, MAY_WRITE) != 0)
-		    && (current->uid != server->m.mounted_uid))
+		    && (current->act_as->uid != server->m.mounted_uid))
 		{
 			return -EACCES;
 		}
@@ -478,7 +478,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 		
         case NCP_IOC_SIGN_WANTED:
 		if ((file_permission(filp, MAY_READ) != 0)
-		    && (current->uid != server->m.mounted_uid))
+		    && (current->act_as->uid != server->m.mounted_uid))
 		{
 			return -EACCES;
 		}
@@ -491,7 +491,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 			int newstate;
 
 			if ((file_permission(filp, MAY_WRITE) != 0)
-			    && (current->uid != server->m.mounted_uid))
+			    && (current->act_as->uid != server->m.mounted_uid))
 			{
 				return -EACCES;
 			}
@@ -512,7 +512,7 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 #ifdef CONFIG_NCPFS_IOCTL_LOCKING
 	case NCP_IOC_LOCKUNLOCK:
 		if ((file_permission(filp, MAY_WRITE) != 0)
-		    && (current->uid != server->m.mounted_uid))
+		    && (current->act_as->uid != server->m.mounted_uid))
 		{
 			return -EACCES;
 		}
@@ -585,7 +585,7 @@ outrel:
 
 #ifdef CONFIG_COMPAT
 	case NCP_IOC_GETOBJECTNAME_32:
-		if (current->uid != server->m.mounted_uid) {
+		if (current->act_as->uid != server->m.mounted_uid) {
 			return -EACCES;
 		}
 		{
@@ -610,7 +610,7 @@ outrel:
 		}
 #endif
 	case NCP_IOC_GETOBJECTNAME:
-		if (current->uid != server->m.mounted_uid) {
+		if (current->act_as->uid != server->m.mounted_uid) {
 			return -EACCES;
 		}
 		{
@@ -637,7 +637,7 @@ outrel:
 	case NCP_IOC_SETOBJECTNAME_32:
 #endif
 	case NCP_IOC_SETOBJECTNAME:
-		if (current->uid != server->m.mounted_uid) {
+		if (current->act_as->uid != server->m.mounted_uid) {
 			return -EACCES;
 		}
 		{
@@ -695,7 +695,7 @@ outrel:
 	case NCP_IOC_GETPRIVATEDATA_32:
 #endif
 	case NCP_IOC_GETPRIVATEDATA:
-		if (current->uid != server->m.mounted_uid) {
+		if (current->act_as->uid != server->m.mounted_uid) {
 			return -EACCES;
 		}
 		{
@@ -740,7 +740,7 @@ outrel:
 	case NCP_IOC_SETPRIVATEDATA_32:
 #endif
 	case NCP_IOC_SETPRIVATEDATA:
-		if (current->uid != server->m.mounted_uid) {
+		if (current->act_as->uid != server->m.mounted_uid) {
 			return -EACCES;
 		}
 		{
@@ -795,7 +795,7 @@ outrel:
 
 	case NCP_IOC_SETDENTRYTTL:
 		if ((file_permission(filp, MAY_WRITE) != 0) &&
-				 (current->uid != server->m.mounted_uid))
+		    current->act_as->uid != server->m.mounted_uid)
 			return -EACCES;
 		{
 			u_int32_t user;
fs/nfsd/auth.c +12 -10
index d13403e..5586157 100644
@@ -26,6 +26,7 @@ int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
 
 int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 {
+	struct task_security *act_as = current->act_as;
 	struct svc_cred	cred = rqstp->rq_cred;
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
@@ -54,25 +55,26 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 		get_group_info(cred.cr_group_info);
 
 	if (cred.cr_uid != (uid_t) -1)
-		current->fsuid = cred.cr_uid;
+		act_as->fsuid = cred.cr_uid;
 	else
-		current->fsuid = exp->ex_anon_uid;
+		act_as->fsuid = exp->ex_anon_uid;
 	if (cred.cr_gid != (gid_t) -1)
-		current->fsgid = cred.cr_gid;
+		act_as->fsgid = cred.cr_gid;
 	else
-		current->fsgid = exp->ex_anon_gid;
+		act_as->fsgid = exp->ex_anon_gid;
 
 	if (!cred.cr_group_info)
 		return -ENOMEM;
-	ret = set_current_groups(cred.cr_group_info);
+	ret = set_groups(act_as, cred.cr_group_info);
 	put_group_info(cred.cr_group_info);
 	if ((cred.cr_uid)) {
-		current->cap_effective =
-			cap_drop_nfsd_set(current->cap_effective);
+		act_as->cap_effective =
+			cap_drop_nfsd_set(act_as->cap_effective);
 	} else {
-		current->cap_effective =
-			cap_raise_nfsd_set(current->cap_effective,
-					   current->cap_permitted);
+		act_as->cap_effective =
+			cap_raise_nfsd_set(act_as->cap_effective,
+					   act_as->cap_permitted);
 	}
 	return ret;
 }
+
fs/nfsd/nfs4recover.c +6 -6
index 1602cd0..bf0217a 100644
@@ -56,17 +56,17 @@ static int rec_dir_init = 0;
 static void
 nfs4_save_user(uid_t *saveuid, gid_t *savegid)
 {
-	*saveuid = current->fsuid;
-	*savegid = current->fsgid;
-	current->fsuid = 0;
-	current->fsgid = 0;
+	*saveuid = current->act_as->fsuid;
+	*savegid = current->act_as->fsgid;
+	current->act_as->fsuid = 0;
+	current->act_as->fsgid = 0;
 }
 
 static void
 nfs4_reset_user(uid_t saveuid, gid_t savegid)
 {
-	current->fsuid = saveuid;
-	current->fsgid = savegid;
+	current->act_as->fsuid = saveuid;
+	current->act_as->fsgid = savegid;
 }
 
 static void
fs/open.c +11 -11
index 4932b4d..6d7a29c 100644
@@ -428,12 +428,12 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
 		return -EINVAL;
 
-	old_fsuid = current->fsuid;
-	old_fsgid = current->fsgid;
-	old_cap = current->cap_effective;
+	old_fsuid = current->act_as->fsuid;
+	old_fsgid = current->act_as->fsgid;
+	old_cap = current->act_as->cap_effective;
 
-	current->fsuid = current->uid;
-	current->fsgid = current->gid;
+	current->act_as->fsuid = current->act_as->uid;
+	current->act_as->fsgid = current->act_as->gid;
 
 	/*
 	 * Clear the capabilities if we switch to a non-root user
@@ -443,10 +443,10 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 	 * value below.  We should hold task_capabilities_lock,
 	 * but we cannot because user_path_walk can sleep.
 	 */
-	if (current->uid)
-		cap_clear(current->cap_effective);
+	if (current->act_as->uid)
+		cap_clear(current->act_as->cap_effective);
 	else
-		current->cap_effective = current->cap_permitted;
+		current->act_as->cap_effective = current->act_as->cap_permitted;
 
 	res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
 	if (res)
@@ -464,9 +464,9 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 out_path_release:
 	path_release(&nd);
 out:
-	current->fsuid = old_fsuid;
-	current->fsgid = old_fsgid;
-	current->cap_effective = old_cap;
+	current->act_as->fsuid = old_fsuid;
+	current->act_as->fsgid = old_fsgid;
+	current->act_as->cap_effective = old_cap;
 
 	return res;
 }
fs/proc/array.c +9 -7
index 6ba2746..f923a3b 100644
@@ -177,8 +177,8 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 		task_tgid_nr_ns(p, ns),
 		task_pid_nr_ns(p, ns),
 		ppid, tpid,
-		p->uid, p->euid, p->suid, p->fsuid,
-		p->gid, p->egid, p->sgid, p->fsgid);
+		p->sec->uid, p->sec->euid, p->sec->suid, p->sec->fsuid,
+		p->sec->gid, p->sec->egid, p->sec->sgid, p->sec->fsgid);
 
 	task_lock(p);
 	if (p->files)
@@ -189,7 +189,7 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 		fdt ? fdt->max_fds : 0);
 	rcu_read_unlock();
 
-	group_info = p->group_info;
+	group_info = p->sec->group_info;
 	get_group_info(group_info);
 	task_unlock(p);
 
@@ -262,7 +262,7 @@ static inline char *task_sig(struct task_struct *p, char *buffer)
 		blocked = p->blocked;
 		collect_sigign_sigcatch(p, &ignored, &caught);
 		num_threads = atomic_read(&p->signal->count);
-		qsize = atomic_read(&p->user->sigpending);
+		qsize = atomic_read(&p->sec->user->sigpending);
 		qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
 		unlock_task_sighand(p, &flags);
 	}
@@ -295,9 +295,11 @@ static char *render_cap_t(const char *header, kernel_cap_t *a, char *buffer)
 
 static inline char *task_cap(struct task_struct *p, char *buffer)
 {
-	buffer = render_cap_t("CapInh:\t", &p->cap_inheritable, buffer);
-	buffer = render_cap_t("CapPrm:\t", &p->cap_permitted, buffer);
-	return render_cap_t("CapEff:\t", &p->cap_effective, buffer);
+	struct task_security *sec = p->sec;
+
+	buffer = render_cap_t("CapInh:\t", &sec->cap_inheritable, buffer);
+	buffer = render_cap_t("CapPrm:\t", &sec->cap_permitted, buffer);
+	return render_cap_t("CapEff:\t", &sec->cap_effective, buffer);
 }
 
 static inline char *task_context_switch_counts(struct task_struct *p,
fs/proc/base.c +8 -8
index c59852b..a5ab3f7 100644
@@ -1233,8 +1233,8 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st
 	inode->i_uid = 0;
 	inode->i_gid = 0;
 	if (task_dumpable(task)) {
-		inode->i_uid = task->euid;
-		inode->i_gid = task->egid;
+		inode->i_uid = task->sec->euid;
+		inode->i_gid = task->sec->egid;
 	}
 	security_task_to_inode(task, inode);
 
@@ -1259,8 +1259,8 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat
 	if (task) {
 		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
 		    task_dumpable(task)) {
-			stat->uid = task->euid;
-			stat->gid = task->egid;
+			stat->uid = task->sec->euid;
+			stat->gid = task->sec->egid;
 		}
 	}
 	rcu_read_unlock();
@@ -1291,8 +1291,8 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 	if (task) {
 		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
 		    task_dumpable(task)) {
-			inode->i_uid = task->euid;
-			inode->i_gid = task->egid;
+			inode->i_uid = task->sec->euid;
+			inode->i_gid = task->sec->egid;
 		} else {
 			inode->i_uid = 0;
 			inode->i_gid = 0;
@@ -1465,8 +1465,8 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 				rcu_read_unlock();
 				put_files_struct(files);
 				if (task_dumpable(task)) {
-					inode->i_uid = task->euid;
-					inode->i_gid = task->egid;
+					inode->i_uid = task->sec->euid;
+					inode->i_gid = task->sec->egid;
 				} else {
 					inode->i_uid = 0;
 					inode->i_gid = 0;
fs/proc/proc_sysctl.c +2 -2
index 4e57fcf..e4ddfdb 100644
@@ -393,9 +393,9 @@ static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *
 	error = -EACCES;
 	mode = inode->i_mode;
 
-	if (current->euid == 0)
+	if (current->act_as->euid == 0)
 		mode >>= 6;
-	else if (in_group_p(0))
+	else if (in_egroup_p(0))
 		mode >>= 3;
 
 	if ((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)
fs/quota.c +2 -2
index 84f28dd..afde3cb 100644
@@ -80,7 +80,7 @@ static int generic_quotactl_valid(struct super_block *sb, int type, int cmd, qid
 
 	/* Check privileges */
 	if (cmd == Q_GETQUOTA) {
-		if (((type == USRQUOTA && current->euid != id) ||
+		if (((type == USRQUOTA && current->act_as->euid != id) ||
 		     (type == GRPQUOTA && !in_egroup_p(id))) &&
 		    !capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -131,7 +131,7 @@ static int xqm_quotactl_valid(struct super_block *sb, int type, int cmd, qid_t i
 
 	/* Check privileges */
 	if (cmd == Q_XGETQUOTA) {
-		if (((type == XQM_USRQUOTA && current->euid != id) ||
+		if (((type == XQM_USRQUOTA && current->act_as->euid != id) ||
 		     (type == XQM_GRPQUOTA && !in_egroup_p(id))) &&
 		     !capable(CAP_SYS_ADMIN))
 			return -EPERM;
fs/smbfs/dir.c +2 -2
index 48da4fa..53e03a3 100644
@@ -667,8 +667,8 @@ smb_make_node(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 
 	attr.ia_valid = ATTR_MODE | ATTR_UID | ATTR_GID;
 	attr.ia_mode = mode;
-	attr.ia_uid = current->euid;
-	attr.ia_gid = current->egid;
+	attr.ia_uid = current->act_as->euid;
+	attr.ia_gid = current->act_as->egid;
 
 	if (!new_valid_dev(dev))
 		return -EINVAL;
fs/smbfs/inode.c +1 -1
index 4e5c22c..6afce17 100644
@@ -586,7 +586,7 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent)
 		if (parse_options(mnt, raw_data))
 			goto out_bad_option;
 	}
-	mnt->mounted_uid = current->uid;
+	mnt->mounted_uid = current->act_as->uid;
 	smb_setcodepage(server, &mnt->codepage);
 
 	/*
fs/smbfs/proc.c +1 -1
index d517a27..a55d9cd 100644
@@ -865,7 +865,7 @@ smb_newconn(struct smb_sb_info *server, struct smb_conn_opt *opt)
 		goto out;
 
 	error = -EACCES;
-	if (current->uid != server->mnt->mounted_uid && 
+	if (current->act_as->uid != server->mnt->mounted_uid &&
 	    !capable(CAP_SYS_ADMIN))
 		goto out;
 
include/linux/init_task.h +18 -7
index 1f74e1d..a26c30e 100644
@@ -133,6 +133,21 @@ extern struct group_info init_groups;
 # define CAP_INIT_BSET  CAP_INIT_EFF_SET
 #endif
 
+extern struct task_security init_task_security;
+
+#define INIT_TASK_SECURITY(p)					\
+{								\
+	.usage			= ATOMIC_INIT(3),		\
+	.keep_capabilities	= 0,				\
+	.cap_inheritable	= CAP_INIT_INH_SET,		\
+	.cap_permitted		= CAP_FULL_SET,			\
+	.cap_effective		= CAP_INIT_EFF_SET,		\
+	.cap_bset		= CAP_INIT_BSET,		\
+	.user			= INIT_USER,			\
+	.group_info		= &init_groups,			\
+	.lock			= __SPIN_LOCK_UNLOCKED(p.lock),	\
+}
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -164,13 +179,9 @@ extern struct group_info init_groups;
 	.children	= LIST_HEAD_INIT(tsk.children),			\
 	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
 	.group_leader	= &tsk,						\
-	.group_info	= &init_groups,					\
-	.cap_effective	= CAP_INIT_EFF_SET,				\
-	.cap_inheritable = CAP_INIT_INH_SET,				\
-	.cap_permitted	= CAP_FULL_SET,					\
-	.cap_bset 	= CAP_INIT_BSET,				\
-	.keep_capabilities = 0,						\
-	.user		= INIT_USER,					\
+	.__temp_sec	= INIT_TASK_SECURITY(tsk.__temp_sec),		\
+	.sec		= &tsk.__temp_sec,				\
+	.act_as		= &tsk.__temp_sec,				\
 	.comm		= "swapper",					\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
include/linux/sched.h +63 -17

110 lines not on this page · raw message

include/net/scm.h +2 -2
index 06df126..b133114 100644
@@ -54,8 +54,8 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg,
 			       struct scm_cookie *scm)
 {
 	struct task_struct *p = current;
-	scm->creds.uid = p->uid;
-	scm->creds.gid = p->gid;
+	scm->creds.uid = p->sec->uid;
+	scm->creds.gid = p->sec->gid;
 	scm->creds.pid = task_tgid_vnr(p);
 	scm->fp = NULL;
 	scm->seq = 0;
ipc/mqueue.c +2 -2
index 590045a..43a3228 100644
@@ -118,7 +118,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode,
 		if (S_ISREG(mode)) {
 			struct mqueue_inode_info *info;
 			struct task_struct *p = current;
-			struct user_struct *u = p->user;
+			struct user_struct *u = p->sec->user;
 			unsigned long mq_bytes, mq_msg_tblsz;
 
 			inode->i_fop = &mqueue_file_operations;
@@ -511,7 +511,7 @@ static void __do_notify(struct mqueue_inode_info *info)
 			sig_i.si_code = SI_MESGQ;
 			sig_i.si_value = info->notify.sigev_value;
 			sig_i.si_pid = task_pid_vnr(current);
-			sig_i.si_uid = current->uid;
+			sig_i.si_uid = current->act_as->uid;
 
 			kill_pid_info(info->notify.sigev_signo,
 				      &sig_i, info->notify_owner);
ipc/msg.c +2 -2
index ec0c724..9599b6b 100644
@@ -562,8 +562,8 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
 	}
 
 	err = -EPERM;
-	if (current->euid != ipcp->cuid &&
-	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN))
+	if (current->act_as->euid != ipcp->cuid &&
+	    current->act_as->euid != ipcp->uid && !capable(CAP_SYS_ADMIN))
 		/* We _could_ check for CAP_CHOWN above, but we don't */
 		goto out_unlock_up;
 
ipc/sem.c +2 -2
index d65e285..31de57a 100644
@@ -935,8 +935,8 @@ static int semctl_down(struct ipc_namespace *ns, int semid, int semnum,
 		if (err)
 			goto out_unlock;
 	}
-	if (current->euid != ipcp->cuid && 
-	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) {
+	if (current->act_as->euid != ipcp->cuid &&
+	    current->act_as->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) {
 	    	err=-EPERM;
 		goto out_unlock;
 	}
ipc/shm.c +8 -8
index 65c3a29..9cfaf3d 100644
@@ -431,7 +431,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (shmflg & SHM_HUGETLB) {
 		/* hugetlb_file_setup takes care of mlock user accounting */
 		file = hugetlb_file_setup(name, size);
-		shp->mlock_user = current->user;
+		shp->mlock_user = current->sec->user;
 	} else {
 		int acctflag = VM_ACCOUNT;
 		/*
@@ -784,8 +784,8 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 
 		if (!capable(CAP_IPC_LOCK)) {
 			err = -EPERM;
-			if (current->euid != shp->shm_perm.uid &&
-			    current->euid != shp->shm_perm.cuid)
+			if (current->act_as->euid != shp->shm_perm.uid &&
+			    current->act_as->euid != shp->shm_perm.cuid)
 				goto out_unlock;
 			if (cmd == SHM_LOCK &&
 			    !current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur)
@@ -797,7 +797,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 			goto out_unlock;
 		
 		if(cmd==SHM_LOCK) {
-			struct user_struct * user = current->user;
+			struct user_struct *user = current->act_as->user;
 			if (!is_file_hugepages(shp->shm_file)) {
 				err = shmem_lock(shp->shm_file, 1, user);
 				if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){
@@ -836,8 +836,8 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 		if (err)
 			goto out_unlock_up;
 
-		if (current->euid != shp->shm_perm.uid &&
-		    current->euid != shp->shm_perm.cuid && 
+		if (current->act_as->euid != shp->shm_perm.uid &&
+		    current->act_as->euid != shp->shm_perm.cuid &&
 		    !capable(CAP_SYS_ADMIN)) {
 			err=-EPERM;
 			goto out_unlock_up;
@@ -876,8 +876,8 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 		if (err)
 			goto out_unlock_up;
 		err=-EPERM;
-		if (current->euid != shp->shm_perm.uid &&
-		    current->euid != shp->shm_perm.cuid && 
+		if (current->act_as->euid != shp->shm_perm.uid &&
+		    current->act_as->euid != shp->shm_perm.cuid &&
 		    !capable(CAP_SYS_ADMIN)) {
 			goto out_unlock_up;
 		}
ipc/util.c +4 -3
index 76c1f34..043dcb7 100644
@@ -283,8 +283,8 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 
 	ids->in_use++;
 
-	new->cuid = new->uid = current->euid;
-	new->gid = new->cgid = current->egid;
+	new->cuid = new->uid = current->act_as->euid;
+	new->gid = new->cgid = current->act_as->egid;
 
 	new->seq = ids->seq++;
 	if(ids->seq > ids->seq_max)
@@ -632,7 +632,8 @@ int ipcperms (struct kern_ipc_perm *ipcp, short flag)
 		return err;
 	requested_mode = (flag >> 6) | (flag >> 3) | flag;
 	granted_mode = ipcp->mode;
-	if (current->euid == ipcp->cuid || current->euid == ipcp->uid)
+	if (current->act_as->euid == ipcp->cuid ||
+	    current->act_as->euid == ipcp->uid)
 		granted_mode >>= 6;
 	else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid))
 		granted_mode >>= 3;
kernel/acct.c +4 -4
index 521dfa5..f2d1783 100644
@@ -470,15 +470,15 @@ static void do_acct_process(struct file *file)
 	do_div(elapsed, AHZ);
 	ac.ac_btime = get_seconds() - elapsed;
 	/* we really need to bite the bullet and change layout */
-	ac.ac_uid = current->uid;
-	ac.ac_gid = current->gid;
+	ac.ac_uid = current->sec->uid;
+	ac.ac_gid = current->sec->gid;
 #if ACCT_VERSION==2
 	ac.ac_ahz = AHZ;
 #endif
 #if ACCT_VERSION==1 || ACCT_VERSION==2
 	/* backward-compatible 16 bit fields */
-	ac.ac_uid16 = current->uid;
-	ac.ac_gid16 = current->gid;
+	ac.ac_uid16 = current->sec->uid;
+	ac.ac_gid16 = current->sec->gid;
 #endif
 #if ACCT_VERSION==3
 	ac.ac_pid = current->tgid;
kernel/auditsc.c +24 -22

120 lines not on this page · raw message

kernel/cgroup.c +3 -2
index 87c5f1e..681de68 100644
@@ -1277,8 +1277,9 @@ static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf)
 		get_task_struct(tsk);
 		rcu_read_unlock();
 
-		if ((current->euid) && (current->euid != tsk->uid)
-		    && (current->euid != tsk->suid)) {
+		if (current->act_as->euid &&
+		    current->act_as->euid != tsk->sec->uid &&
+		    current->act_as->euid != tsk->sec->suid) {
 			put_task_struct(tsk);
 			return -EACCES;
 		}
kernel/exit.c +6 -6
index eb9934a..910c793 100644
@@ -145,7 +145,7 @@ void release_task(struct task_struct * p)
 	struct task_struct *leader;
 	int zap_leader;
 repeat:
-	atomic_dec(&p->user->processes);
+	atomic_dec(&p->sec->user->processes);
 	proc_flush_task(p);
 	write_lock_irq(&tasklist_lock);
 	ptrace_unlink(p);
@@ -1197,7 +1197,7 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
 
 	if (unlikely(noreap)) {
 		pid_t pid = task_pid_nr_ns(p, ns);
-		uid_t uid = p->uid;
+		uid_t uid = p->sec->uid;
 		int exit_code = p->exit_code;
 		int why, status;
 
@@ -1317,7 +1317,7 @@ static int wait_task_zombie(struct task_struct *p, int noreap,
 	if (!retval && infop)
 		retval = put_user(task_pid_nr_ns(p, ns), &infop->si_pid);
 	if (!retval && infop)
-		retval = put_user(p->uid, &infop->si_uid);
+		retval = put_user(p->sec->uid, &infop->si_uid);
 	if (!retval)
 		retval = task_pid_nr_ns(p, ns);
 
@@ -1380,7 +1380,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader,
 	read_unlock(&tasklist_lock);
 
 	if (unlikely(noreap)) {
-		uid_t uid = p->uid;
+		uid_t uid = p->sec->uid;
 		int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED;
 
 		exit_code = p->exit_code;
@@ -1451,7 +1451,7 @@ bail_ref:
 	if (!retval && infop)
 		retval = put_user(pid, &infop->si_pid);
 	if (!retval && infop)
-		retval = put_user(p->uid, &infop->si_uid);
+		retval = put_user(p->sec->uid, &infop->si_uid);
 	if (!retval)
 		retval = pid;
 	put_task_struct(p);
@@ -1490,7 +1490,7 @@ static int wait_task_continued(struct task_struct *p, int noreap,
 
 	ns = current->nsproxy->pid_ns;
 	pid = task_pid_nr_ns(p, ns);
-	uid = p->uid;
+	uid = p->sec->uid;
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
 
kernel/fork.c +12 -12
index b2ef8e4..6580020 100644
@@ -124,8 +124,8 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(tsk == current);
 
 	security_task_free(tsk);
-	free_uid(tsk->user);
-	put_group_info(tsk->group_info);
+	free_uid(tsk->__temp_sec.user);
+	put_group_info(tsk->__temp_sec.group_info);
 	delayacct_tsk_free(tsk);
 
 	if (!profile_handoff_task(tsk))
@@ -1046,17 +1046,18 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
+	p->act_as = p->sec = &p->__temp_sec;
 	retval = -EAGAIN;
-	if (atomic_read(&p->user->processes) >=
+	if (atomic_read(&p->sec->user->processes) >=
 			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
 		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
-		    p->user != current->nsproxy->user_ns->root_user)
+		    p->sec->user != current->nsproxy->user_ns->root_user)
 			goto bad_fork_free;
 	}
 
-	atomic_inc(&p->user->__count);
-	atomic_inc(&p->user->processes);
-	get_group_info(p->group_info);
+	atomic_inc(&p->sec->user->__count);
+	atomic_inc(&p->sec->user->processes);
+	get_group_info(p->sec->group_info);
 
 	/*
 	 * If multiple threads are within copy_process(), then this check
@@ -1121,9 +1122,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = p->start_time;
 	monotonic_to_bootbased(&p->real_start_time);
 #ifdef CONFIG_SECURITY
-	p->security = NULL;
+	p->sec->security = NULL;
 #endif
-	p->cap_bset = current->cap_bset;
 	p->io_context = NULL;
 	p->audit_context = NULL;
 	cgroup_fork(p);
@@ -1395,9 +1395,9 @@ bad_fork_cleanup_cgroup:
 bad_fork_cleanup_put_domain:
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
-	put_group_info(p->group_info);
-	atomic_dec(&p->user->processes);
-	free_uid(p->user);
+	put_group_info(p->sec->group_info);
+	atomic_dec(&p->sec->user->processes);
+	free_uid(p->sec->user);
 bad_fork_free:
 	free_task(p);
 fork_out:
kernel/futex.c +5 -3
index a6baaec..fa25e20 100644
@@ -447,7 +447,8 @@ static struct task_struct * futex_find_get_task(pid_t pid)
 
 	rcu_read_lock();
 	p = find_task_by_vpid(pid);
-	if (!p || ((current->euid != p->euid) && (current->euid != p->uid)))
+	if (!p || (current->act_as->euid != p->sec->euid &&
+		   current->act_as->euid != p->sec->uid))
 		p = ERR_PTR(-ESRCH);
 	else
 		get_task_struct(p);
@@ -1905,8 +1906,9 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
 		if (!p)
 			goto err_unlock;
 		ret = -EPERM;
-		if ((current->euid != p->euid) && (current->euid != p->uid) &&
-				!capable(CAP_SYS_PTRACE))
+		if (current->act_as->euid != p->sec->euid &&
+		    current->act_as->euid != p->sec->uid &&
+		    !capable(CAP_SYS_PTRACE))
 			goto err_unlock;
 		head = p->robust_list;
 		rcu_read_unlock();
kernel/futex_compat.c +3 -2
index 133d558..51f46cd 100644
@@ -141,8 +141,9 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 		if (!p)
 			goto err_unlock;
 		ret = -EPERM;
-		if ((current->euid != p->euid) && (current->euid != p->uid) &&
-				!capable(CAP_SYS_PTRACE))
+		if (current->act_as->euid != p->sec->euid &&
+		    current->act_as->euid != p->sec->uid &&
+		    !capable(CAP_SYS_PTRACE))
 			goto err_unlock;
 		head = p->compat_robust_list;
 		read_unlock(&tasklist_lock);
kernel/ptrace.c +8 -6
index 628b03a..3ecc9e1 100644
@@ -121,6 +121,8 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 
 int __ptrace_may_attach(struct task_struct *task)
 {
+	struct task_security *sec = current->act_as, *tsec = task->sec;
+
 	/* May we inspect the given task?
 	 * This check is used both for attaching with ptrace
 	 * and for allowing access to sensitive information in /proc.
@@ -133,12 +135,12 @@ int __ptrace_may_attach(struct task_struct *task)
 	/* Don't let security modules deny introspection */
 	if (task == current)
 		return 0;
-	if (((current->uid != task->euid) ||
-	     (current->uid != task->suid) ||
-	     (current->uid != task->uid) ||
-	     (current->gid != task->egid) ||
-	     (current->gid != task->sgid) ||
-	     (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
+	if (((sec->uid != tsec->euid) ||
+	     (sec->uid != tsec->suid) ||
+	     (sec->uid != tsec->uid) ||
+	     (sec->gid != tsec->egid) ||
+	     (sec->gid != tsec->sgid) ||
+	     (sec->gid != tsec->gid)) && !capable(CAP_SYS_PTRACE))
 		return -EPERM;
 	smp_rmb();
 	if (task->mm)
kernel/sched.c +6 -5
index 9474b23..7f6d603 100644
@@ -275,7 +275,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct task_group *tg;
 
 #ifdef CONFIG_FAIR_USER_SCHED
-	tg = p->user->tg;
+	tg = p->sec->user->tg;
 #elif defined(CONFIG_FAIR_CGROUP_SCHED)
 	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
 				struct task_group, css);
@@ -4566,8 +4566,8 @@ recheck:
 			return -EPERM;
 
 		/* can't change other user's priorities */
-		if ((current->euid != p->euid) &&
-		    (current->euid != p->uid))
+		if ((current->act_as->euid != p->sec->euid) &&
+		    (current->act_as->euid != p->sec->uid))
 			return -EPERM;
 	}
 
@@ -4756,8 +4756,9 @@ long sched_setaffinity(pid_t pid, cpumask_t new_mask)
 	read_unlock(&tasklist_lock);
 
 	retval = -EPERM;
-	if ((current->euid != p->euid) && (current->euid != p->uid) &&
-			!capable(CAP_SYS_NICE))
+	if ((current->act_as->euid != p->sec->euid) &&
+	    (current->act_as->euid != p->sec->uid) &&
+	    !capable(CAP_SYS_NICE))
 		goto out_unlock;
 
 	retval = security_task_setscheduler(p, 0, NULL);
kernel/signal.c +14 -12
index 5d30ff5..76e3fd9 100644
@@ -174,7 +174,7 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
 	 * In order to avoid problems with "switch_user()", we want to make
 	 * sure that the compiler doesn't re-load "t->user"
 	 */
-	user = t->user;
+	user = t->sec->user;
 	barrier();
 	atomic_inc(&user->sigpending);
 	if (override_rlimit ||
@@ -537,8 +537,10 @@ static int check_kill_permission(int sig, struct siginfo *info,
 		error = -EPERM;
 		if (((sig != SIGCONT) ||
 			(task_session_nr(current) != task_session_nr(t)))
-		    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
-		    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
+		    && (current->act_as->euid ^ t->sec->suid)
+		    && (current->act_as->euid ^ t->sec->uid)
+		    && (current->act_as->uid ^ t->sec->suid)
+		    && (current->act_as->uid ^ t->sec->uid)
 		    && !capable(CAP_KILL))
 		return error;
 	}
@@ -695,7 +697,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			q->info.si_errno = 0;
 			q->info.si_code = SI_USER;
 			q->info.si_pid = task_pid_vnr(current);
-			q->info.si_uid = current->uid;
+			q->info.si_uid = current->act_as->uid;
 			break;
 		case (unsigned long) SEND_SIG_PRIV:
 			q->info.si_signo = sig;
@@ -1095,8 +1097,8 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
 		goto out_unlock;
 	}
 	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
-	    && (euid != p->suid) && (euid != p->uid)
-	    && (uid != p->suid) && (uid != p->uid)) {
+	    && (euid != p->sec->suid) && (euid != p->sec->uid)
+	    && (uid != p->sec->suid) && (uid != p->sec->uid)) {
 		ret = -EPERM;
 		goto out_unlock;
 	}
@@ -1448,7 +1450,7 @@ void do_notify_parent(struct task_struct *tsk, int sig)
 	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
 	rcu_read_unlock();
 
-	info.si_uid = tsk->uid;
+	info.si_uid = tsk->sec->uid;
 
 	/* FIXME: find out whether or not this is supposed to be c*time. */
 	info.si_utime = cputime_to_jiffies(cputime_add(tsk->utime,
@@ -1519,7 +1521,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 	info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
 	rcu_read_unlock();
 
-	info.si_uid = tsk->uid;
+	info.si_uid = tsk->sec->uid;
 
 	/* FIXME: find out whether or not this is supposed to be c*time. */
 	info.si_utime = cputime_to_jiffies(tsk->utime);
@@ -1676,7 +1678,7 @@ void ptrace_notify(int exit_code)
 	info.si_signo = SIGTRAP;
 	info.si_code = exit_code;
 	info.si_pid = task_pid_vnr(current);
-	info.si_uid = current->uid;
+	info.si_uid = current->sec->uid;
 
 	/* Let the debugger run.  */
 	spin_lock_irq(&current->sighand->siglock);
@@ -1805,7 +1807,7 @@ relock:
 				info->si_errno = 0;
 				info->si_code = SI_USER;
 				info->si_pid = task_pid_vnr(current->parent);
-				info->si_uid = current->parent->uid;
+				info->si_uid = current->parent->sec->uid;
 			}
 
 			/* If the (new) signal is now blocked, requeue it.  */
@@ -2192,7 +2194,7 @@ sys_kill(int pid, int sig)
 	info.si_errno = 0;
 	info.si_code = SI_USER;
 	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = current->uid;
+	info.si_uid = current->act_as->uid;
 
 	return kill_something_info(sig, &info, pid);
 }
@@ -2208,7 +2210,7 @@ static int do_tkill(int tgid, int pid, int sig)
 	info.si_errno = 0;
 	info.si_code = SI_TKILL;
 	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = current->uid;
+	info.si_uid = current->act_as->uid;
 
 	read_lock(&tasklist_lock);
 	p = find_task_by_vpid(pid);
kernel/sys.c +155 -123

617 lines not on this page · raw message

kernel/sysctl.c +1 -1
index 8c98d81..2dcab35 100644
@@ -1514,7 +1514,7 @@ out:
 
 static int test_perm(int mode, int op)
 {
-	if (!current->euid)
+	if (!current->act_as->euid)
 		mode >>= 6;
 	else if (in_egroup_p(0))
 		mode >>= 3;
kernel/timer.c +4 -4
index 70b29b5..4a4c77e 100644
@@ -988,25 +988,25 @@ asmlinkage long sys_getppid(void)
 asmlinkage long sys_getuid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->uid;
+	return current->sec->uid;
 }
 
 asmlinkage long sys_geteuid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->euid;
+	return current->sec->euid;
 }
 
 asmlinkage long sys_getgid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->gid;
+	return current->sec->gid;
 }
 
 asmlinkage long sys_getegid(void)
 {
 	/* Only we change this so SMP safe */
-	return  current->egid;
+	return  current->sec->egid;
 }
 
 #endif
kernel/tsacct.c +2 -2
index 4ab1b58..84c98ee 100644
@@ -53,8 +53,8 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 		stats->ac_flag |= AXSIG;
 	stats->ac_nice	 = task_nice(tsk);
 	stats->ac_sched	 = tsk->policy;
-	stats->ac_uid	 = tsk->uid;
-	stats->ac_gid	 = tsk->gid;
+	stats->ac_uid	 = tsk->sec->uid;
+	stats->ac_gid	 = tsk->sec->gid;
 	stats->ac_pid	 = tsk->pid;
 	rcu_read_lock();
 	stats->ac_ppid	 = pid_alive(tsk) ?
kernel/uid16.c +14 -14
index dd308ba..c56f6fe 100644
@@ -86,9 +86,9 @@ asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid,
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
-	    !(retval = put_user(high2lowuid(current->euid), euid)))
-		retval = put_user(high2lowuid(current->suid), suid);
+	if (!(retval = put_user(high2lowuid(current->sec->uid), ruid)) &&
+	    !(retval = put_user(high2lowuid(current->sec->euid), euid)))
+		retval = put_user(high2lowuid(current->sec->suid), suid);
 
 	return retval;
 }
@@ -106,9 +106,9 @@ asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid,
 {
 	int retval;
 
-	if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
-	    !(retval = put_user(high2lowgid(current->egid), egid)))
-		retval = put_user(high2lowgid(current->sgid), sgid);
+	if (!(retval = put_user(high2lowgid(current->sec->gid), rgid)) &&
+	    !(retval = put_user(high2lowgid(current->sec->egid), egid)))
+		retval = put_user(high2lowgid(current->sec->sgid), sgid);
 
 	return retval;
 }
@@ -166,20 +166,20 @@ asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	get_group_info(current->sec->group_info);
+	i = current->sec->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, current->sec->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
+	put_group_info(current->sec->group_info);
 	return i;
 }
 
@@ -210,20 +210,20 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
 
 asmlinkage long sys_getuid16(void)
 {
-	return high2lowuid(current->uid);
+	return high2lowuid(current->sec->uid);
 }
 
 asmlinkage long sys_geteuid16(void)
 {
-	return high2lowuid(current->euid);
+	return high2lowuid(current->sec->euid);
 }
 
 asmlinkage long sys_getgid16(void)
 {
-	return high2lowgid(current->gid);
+	return high2lowgid(current->sec->gid);
 }
 
 asmlinkage long sys_getegid16(void)
 {
-	return high2lowgid(current->egid);
+	return high2lowgid(current->sec->egid);
 }
kernel/user.c +2 -2
index bc1c48d..3a2151d 100644
@@ -406,11 +406,11 @@ void switch_uid(struct user_struct *new_user)
 	 * cheaply with the new uid cache, so if it matters
 	 * we should be checking for it.  -DaveM
 	 */
-	old_user = current->user;
+	old_user = current->sec->user;
 	atomic_inc(&new_user->processes);
 	atomic_dec(&old_user->processes);
 	switch_uid_keyring(new_user);
-	current->user = new_user;
+	current->sec->user = new_user;
 	sched_switch_user(current);
 
 	/*
kernel/user_namespace.c +1 -1
index 7af90fc..fef8023 100644
@@ -49,7 +49,7 @@ static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
 	}
 
 	/* Reset current->user with a new one */
-	new_user = alloc_uid(ns, current->uid);
+	new_user = alloc_uid(ns, current->sec->uid);
 	if (!new_user) {
 		free_uid(ns->root_user);
 		kfree(ns);
mm/mempolicy.c +5 -2
index 83c69f8..f7a3078 100644
@@ -941,6 +941,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 		const unsigned long __user *old_nodes,
 		const unsigned long __user *new_nodes)
 {
+	struct task_security *act_as, *obj;
 	struct mm_struct *mm;
 	struct task_struct *task;
 	nodemask_t old;
@@ -975,8 +976,10 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	if ((current->euid != task->suid) && (current->euid != task->uid) &&
-	    (current->uid != task->suid) && (current->uid != task->uid) &&
+	act_as = current->act_as;
+	obj = task->sec;
+	if ((act_as->euid != obj->suid) && (act_as->euid != obj->uid) &&
+	    (act_as->uid != obj->suid) && (act_as->uid != obj->uid) &&
 	    !capable(CAP_SYS_NICE)) {
 		err = -EPERM;
 		goto out;
mm/migrate.c +5 -2
index a73504f..75ae1fb 100644
@@ -935,6 +935,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
 			const int __user *nodes,
 			int __user *status, int flags)
 {
+	struct task_security *act_as, *obj;
 	int err = 0;
 	int i;
 	struct task_struct *task;
@@ -968,8 +969,10 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
 	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
-	if ((current->euid != task->suid) && (current->euid != task->uid) &&
-	    (current->uid != task->suid) && (current->uid != task->uid) &&
+	act_as = current->act_as;
+	obj = task->sec;
+	if ((act_as->euid != obj->suid) && (act_as->euid != obj->uid) &&
+	    (act_as->uid != obj->suid) && (act_as->uid != obj->uid) &&
 	    !capable(CAP_SYS_NICE)) {
 		err = -EPERM;
 		goto out2;
mm/oom_kill.c +1 -1
index 4194b9d..82a6710 100644
@@ -291,7 +291,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
 
 		task_lock(p);
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
-		       p->pid, p->uid, p->tgid, p->mm->total_vm,
+		       p->pid, p->sec->uid, p->tgid, p->mm->total_vm,
 		       get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj,
 		       p->comm);
 		task_unlock(p);
net/ax25/af_ax25.c +1 -1
index 8fc64e3..a205008 100644
@@ -1048,7 +1048,7 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (addr->fsa_ax25.sax25_family != AF_AX25)
 		return -EINVAL;
 
-	user = ax25_findbyuid(current->euid);
+	user = ax25_findbyuid(current->act_as->euid);
 	if (user) {
 		call = user->call;
 		ax25_uid_put(user);
net/ax25/ax25_route.c +1 -1
index 38c7f30..0402059 100644
@@ -421,7 +421,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
 		goto put;
 	}
 
-	user = ax25_findbyuid(current->euid);
+	user = ax25_findbyuid(current->act_as->euid);
 	if (user) {
 		ax25->source_addr = user->call;
 		ax25_uid_put(user);
net/core/dev.c +1 -1
index 9549417..0a26796 100644
@@ -2759,7 +2759,7 @@ static void __dev_set_promiscuity(struct net_device *dev, int inc)
 				dev->name, (dev->flags & IFF_PROMISC),
 				(old_flags & IFF_PROMISC),
 				audit_get_loginuid(current),
-				current->uid, current->gid,
+				current->act_as->uid, current->act_as->gid,
 				audit_get_sessionid(current));
 
 		if (dev->change_rx_flags)
net/core/scm.c +6 -4
index 10f5c65..703b174 100644
@@ -44,11 +44,13 @@
 
 static __inline__ int scm_check_creds(struct ucred *creds)
 {
+	struct task_security *sec = current->act_as;
+
 	if ((creds->pid == task_tgid_vnr(current) || capable(CAP_SYS_ADMIN)) &&
-	    ((creds->uid == current->uid || creds->uid == current->euid ||
-	      creds->uid == current->suid) || capable(CAP_SETUID)) &&
-	    ((creds->gid == current->gid || creds->gid == current->egid ||
-	      creds->gid == current->sgid) || capable(CAP_SETGID))) {
+	    ((creds->uid == sec->uid || creds->uid == sec->euid ||
+	      creds->uid == sec->suid) || capable(CAP_SETUID)) &&
+	    ((creds->gid == sec->gid || creds->gid == sec->egid ||
+	      creds->gid == sec->sgid) || capable(CAP_SETGID))) {
 	       return 0;
 	}
 	return -EPERM;
net/ipv6/ip6_flowlabel.c +1 -1
index 2b7d9ee..bda7783 100644
@@ -364,7 +364,7 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *
 		fl->owner = current->pid;
 		break;
 	case IPV6_FL_S_USER:
-		fl->owner = current->euid;
+		fl->owner = current->act_as->euid;
 		break;
 	default:
 		err = -EINVAL;
net/netrom/af_netrom.c +2 -2
index 972250c..2471ff9 100644
@@ -599,7 +599,7 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	} else {
 		source = &addr->fsa_ax25.sax25_call;
 
-		user = ax25_findbyuid(current->euid);
+		user = ax25_findbyuid(current->act_as->euid);
 		if (user) {
 			nr->user_addr   = user->call;
 			ax25_uid_put(user);
@@ -673,7 +673,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
 		}
 		source = (ax25_address *)dev->dev_addr;
 
-		user = ax25_findbyuid(current->euid);
+		user = ax25_findbyuid(current->act_as->euid);
 		if (user) {
 			nr->user_addr   = user->call;
 			ax25_uid_put(user);
net/rose/af_rose.c +2 -2
index 4a31a81..53ff9ce 100644
@@ -669,7 +669,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	source = &addr->srose_call;
 
-	user = ax25_findbyuid(current->euid);
+	user = ax25_findbyuid(current->act_as->euid);
 	if (user) {
 		rose->source_call = user->call;
 		ax25_uid_put(user);
@@ -768,7 +768,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 			goto out_release;
 		}
 
-		user = ax25_findbyuid(current->euid);
+		user = ax25_findbyuid(current->act_as->euid);
 		if (!user) {
 			err = -EINVAL;
 			goto out_release;
net/sunrpc/auth.c +2 -2
index 83e60f8..01e25a2 100644
@@ -345,7 +345,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int flags)
 	struct auth_cred acred = {
 		.uid = current_fsuid(),
 		.gid = current_fsgid(),
-		.group_info = current->group_info,
+		.group_info = current->act_as->group_info,
 	};
 	struct rpc_cred *ret;
 
@@ -382,7 +382,7 @@ rpcauth_bindcred(struct rpc_task *task)
 	struct auth_cred acred = {
 		.uid = current_fsuid(),
 		.gid = current_fsgid(),
-		.group_info = current->group_info,
+		.group_info = current->act_as->group_info,
 	};
 	struct rpc_cred *ret;
 	int flags = 0;
net/unix/af_unix.c +6 -6
index eea7588..5670a62 100644
@@ -464,8 +464,8 @@ static int unix_listen(struct socket *sock, int backlog)
 	sk->sk_state		= TCP_LISTEN;
 	/* set credentials so connect can copy them */
 	sk->sk_peercred.pid	= task_tgid_vnr(current);
-	sk->sk_peercred.uid	= current->euid;
-	sk->sk_peercred.gid	= current->egid;
+	sk->sk_peercred.uid	= current->act_as->euid;
+	sk->sk_peercred.gid	= current->act_as->egid;
 	err = 0;
 
 out_unlock:
@@ -1117,8 +1117,8 @@ restart:
 	newsk->sk_state		= TCP_ESTABLISHED;
 	newsk->sk_type		= sk->sk_type;
 	newsk->sk_peercred.pid	= task_tgid_vnr(current);
-	newsk->sk_peercred.uid	= current->euid;
-	newsk->sk_peercred.gid	= current->egid;
+	newsk->sk_peercred.uid	= current->act_as->euid;
+	newsk->sk_peercred.gid	= current->act_as->egid;
 	newu = unix_sk(newsk);
 	newsk->sk_sleep		= &newu->peer_wait;
 	otheru = unix_sk(other);
@@ -1178,8 +1178,8 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
 	unix_peer(ska)=skb;
 	unix_peer(skb)=ska;
 	ska->sk_peercred.pid = skb->sk_peercred.pid = task_tgid_vnr(current);
-	ska->sk_peercred.uid = skb->sk_peercred.uid = current->euid;
-	ska->sk_peercred.gid = skb->sk_peercred.gid = current->egid;
+	ska->sk_peercred.uid = skb->sk_peercred.uid = current->act_as->euid;
+	ska->sk_peercred.gid = skb->sk_peercred.gid = current->act_as->egid;
 
 	if (ska->sk_type != SOCK_DGRAM) {
 		ska->sk_state = TCP_ESTABLISHED;
security/commoncap.c +70 -55

278 lines not on this page · raw message

security/dummy.c +25 -15
index 6a0056b..28413ae 100644
@@ -36,7 +36,7 @@ static int dummy_ptrace (struct task_struct *parent, struct task_struct *child)
 static int dummy_capget (struct task_struct *target, kernel_cap_t * effective,
 			 kernel_cap_t * inheritable, kernel_cap_t * permitted)
 {
-	if (target->euid == 0) {
+	if (target->sec->euid == 0) {
 		cap_set_full(*permitted);
 		cap_set_init_eff(*effective);
 	} else {
@@ -46,7 +46,7 @@ static int dummy_capget (struct task_struct *target, kernel_cap_t * effective,
 
 	cap_clear(*inheritable);
 
-	if (target->fsuid != 0) {
+	if (target->sec->fsuid != 0) {
 		*permitted = cap_drop_fs_set(*permitted);
 		*effective = cap_drop_fs_set(*effective);
 	}
@@ -76,7 +76,7 @@ static int dummy_acct (struct file *file)
 
 static int dummy_capable (struct task_struct *tsk, int cap)
 {
-	if (cap_raised (tsk->cap_effective, cap))
+	if (cap_raised(tsk->act_as->cap_effective, cap))
 		return 0;
 	return -EPERM;
 }
@@ -98,7 +98,7 @@ static int dummy_quota_on (struct dentry *dentry)
 
 static int dummy_syslog (int type)
 {
-	if ((type != 3 && type != 10) && current->euid)
+	if ((type != 3 && type != 10) && current->act_as->euid)
 		return -EPERM;
 	return 0;
 }
@@ -131,19 +131,24 @@ static void dummy_bprm_free_security (struct linux_binprm *bprm)
 
 static void dummy_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 {
-	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid) {
+	struct task_security *sec = current->sec;
+
+	if (bprm->e_uid != sec->uid || bprm->e_gid != sec->gid) {
 		set_dumpable(current->mm, suid_dumpable);
 
 		if ((unsafe & ~LSM_UNSAFE_PTRACE_CAP) && !capable(CAP_SETUID)) {
-			bprm->e_uid = current->uid;
-			bprm->e_gid = current->gid;
+			bprm->e_uid = sec->uid;
+			bprm->e_gid = sec->gid;
 		}
[… more lines in the raw message]

Lines of this file are not shown. View the raw message.

security/keys/keyctl.c +13 -12
index b3a63dd..4051948 100644

Lines of this file are not shown. View the raw message.

security/keys/permission.c +6 -5
index 3b41f9b..07898bd 100644

Lines of this file are not shown. View the raw message.

security/keys/process_keys.c +39 -37

76 lines not on this page · raw message

security/keys/request_key.c +7 -6
index 21efac2..5b5ad42 100644

Lines of this file are not shown. View the raw message.

security/keys/request_key_auth.c +6 -6
index 980d8cb..d306412 100644

Lines of this file are not shown. View the raw message.

security/selinux/exports.c +2 -2
index 87d2bb3..5a0daa5 100644

Lines of this file are not shown. View the raw message.

security/selinux/hooks.c +56 -55

111 lines not on this page · raw message

security/selinux/selinuxfs.c +1 -1
index 0341567..c245a14 100644

Lines of this file are not shown. View the raw message.

security/selinux/xfrm.c +3 -3
index 7e15820..562f790 100644

Lines of this file are not shown. View the raw message.

The rest of this diff is not shown. View the raw message.

Part of the diff is not shown here. View the raw message.

maintainer Reviewed-by on v1 6/37
#8 lore raw

Re: [PATCH 06/37] Security: Separate task security context from task_struct

Quoted 11 lines · David Howells

Separate the task security context from task_struct. At this point, the security data is temporarily embedded in the task_struct with two pointers pointing to it.

Alpha needs further alteration as it refers to UID & GID in entry.S via asm offsets.

Sparc needs further alteration as it refers to UID & GID in sclow.S via asm offsets.

(SELinux stuff mostly).

Signature · 2 lines
James Morris
<[email protected]>
author maintainer
#9 lore raw

PATCH 7/37 Security: De-embed task security record from task and use refcounting

In reply to David Howells

Remove the temporarily embedded task security record from task_struct. Instead it is made to dangle from the task_struct::sec and task_struct::act_as pointers with references counted for each.

do_coredump() is made to create a copy of the security record, modify it and then use that to override the main one for a task. sys_faccessat() is made to do the same.

The process and session keyrings are moved from signal_struct into a new thread_group_security struct. This is then refcounted, with pointers coming from the task_security struct instead of from signal_struct.

The keyring functions then take pointers to task_security structs rather than task_structs for their security contexts. This is so that request_key() can proceed asynchronously without having to worry about the initiator task's act_as pointer changing.

The LSM hooks for dealing with task security are modified to deal with the task security struct directly rather than going via the task_struct as appopriate.

This permits the subjective security context of a task to be overridden by changing its act_as pointer without altering its objective security pointer, and thus not breaking signalling, ptrace, etc. whilst the override is in force.

---

 fs/exec.c                        |   15 +-
 fs/open.c                        |   37 ++---
 include/linux/init_task.h        |   18 --
 include/linux/key-ui.h           |   10 +
 include/linux/key.h              |   31 +---
 include/linux/sched.h            |   40 ++++-
 include/linux/security.h         |   43 ++++--
 kernel/Makefile                  |    2 
 kernel/cred.c                    |  140 ++++++++++++++++++
 kernel/exit.c                    |    1 
 kernel/fork.c                    |   40 ++---
 kernel/kmod.c                    |   10 +
 kernel/sys.c                     |   16 +-
 kernel/user.c                    |    2 
 net/rxrpc/ar-key.c               |    4 -
 security/dummy.c                 |   14 +-
 security/keys/internal.h         |   10 +
 security/keys/key.c              |    6 -
 security/keys/keyctl.c           |    6 -
 security/keys/keyring.c          |   14 +-
 security/keys/permission.c       |    5 -
 security/keys/proc.c             |    2 
 security/keys/process_keys.c     |  290 +++++++++++++++++---------------------
 security/keys/request_key.c      |   59 ++++----
 security/keys/request_key_auth.c |   38 ++---
 security/security.c              |   20 ++-
 security/selinux/hooks.c         |   46 +++++-
 27 files changed, 527 insertions(+), 392 deletions(-)
 create mode 100644 kernel/cred.c
fs/exec.c +11 -4
index c09a2d9..afbcc34 100644
@@ -1670,13 +1670,13 @@ int get_dumpable(struct mm_struct *mm)
 
 int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 {
+	struct task_security *sec, *old_act_as;
 	char corename[CORENAME_MAX_SIZE + 1];
 	struct mm_struct *mm = current->mm;
 	struct linux_binfmt * binfmt;
 	struct inode * inode;
 	struct file * file;
 	int retval = 0;
-	int fsuid = current_fsuid();
 	int flag = 0;
 	int ispipe = 0;
 	unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur;
@@ -1688,7 +1688,10 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 
 	binfmt = current->binfmt;
 	if (!binfmt || !binfmt->core_dump)
-		goto fail;
+		goto fail_nosubj;
+	sec = dup_task_security(current->sec);
+	if (!sec)
+		goto fail_nosubj;
 	down_write(&mm->mmap_sem);
 	/*
 	 * If another thread got here first, or we are not dumpable, bail out.
@@ -1703,9 +1706,11 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 	 *	process nor do we know its entire history. We only know it
 	 *	was tainted so we dump it as root in mode 2.
 	 */
+	old_act_as = current->act_as;
 	if (get_dumpable(mm) == 2) {	/* Setuid core dump mode */
 		flag = O_EXCL;		/* Stop rewrite attacks */
-		current->act_as->fsuid = 0;	/* Dump root private */
+		sec->fsuid = 0;		/* Dump root private */
+		current->act_as = sec;
 	}
 
 	retval = coredump_wait(exit_code);
@@ -1801,8 +1806,10 @@ fail_unlock:
 	if (helper_argv)
 		argv_free(helper_argv);
 
-	current->act_as->fsuid = fsuid;
+	current->act_as = old_act_as;
 	complete_all(&mm->core_done);
 fail:
+	put_task_security(sec);
+fail_nosubj:
 	return retval;
 }
fs/open.c +14 -23
index 6d7a29c..710102a 100644
@@ -420,34 +420,27 @@ out:
  */
 asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 {
+	struct task_security *sec, *old_act_as;
 	struct nameidata nd;
-	int old_fsuid, old_fsgid;
-	kernel_cap_t old_cap;
 	int res;
 
 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
 		return -EINVAL;
 
-	old_fsuid = current->act_as->fsuid;
-	old_fsgid = current->act_as->fsgid;
-	old_cap = current->act_as->cap_effective;
+	sec = dup_task_security(current->sec);
+	if (!sec)
+		return -ENOMEM;
+	sec->fsuid = current->sec->uid;
+	sec->fsgid = current->sec->gid;
 
-	current->act_as->fsuid = current->act_as->uid;
-	current->act_as->fsgid = current->act_as->gid;
-
-	/*
-	 * Clear the capabilities if we switch to a non-root user
-	 *
-	 * FIXME: There is a race here against sys_capset.  The
-	 * capabilities can change yet we will restore the old
-	 * value below.  We should hold task_capabilities_lock,
-	 * but we cannot because user_path_walk can sleep.
-	 */
-	if (current->act_as->uid)
-		cap_clear(current->act_as->cap_effective);
+	/* Clear the capabilities if we switch to a non-root user */
+	if (current->sec->uid)
+		cap_clear(sec->cap_effective);
 	else
-		current->act_as->cap_effective = current->act_as->cap_permitted;
+		sec->cap_effective = current->sec->cap_permitted;
 
+	old_act_as = current->act_as;
+	current->act_as = sec;
 	res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
 	if (res)
 		goto out;
@@ -464,10 +457,8 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 out_path_release:
 	path_release(&nd);
 out:
-	current->act_as->fsuid = old_fsuid;
-	current->act_as->fsgid = old_fsgid;
-	current->act_as->cap_effective = old_cap;
-
+	current->act_as = old_act_as;
+	put_task_security(sec);
 	return res;
 }
 
include/linux/init_task.h +2 -16
index a26c30e..25bda17 100644
@@ -135,19 +135,6 @@ extern struct group_info init_groups;
 
 extern struct task_security init_task_security;
 
-#define INIT_TASK_SECURITY(p)					\
-{								\
-	.usage			= ATOMIC_INIT(3),		\
-	.keep_capabilities	= 0,				\
-	.cap_inheritable	= CAP_INIT_INH_SET,		\
-	.cap_permitted		= CAP_FULL_SET,			\
-	.cap_effective		= CAP_INIT_EFF_SET,		\
-	.cap_bset		= CAP_INIT_BSET,		\
-	.user			= INIT_USER,			\
-	.group_info		= &init_groups,			\
-	.lock			= __SPIN_LOCK_UNLOCKED(p.lock),	\
-}
-
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -179,9 +166,8 @@ extern struct task_security init_task_security;
 	.children	= LIST_HEAD_INIT(tsk.children),			\
 	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
 	.group_leader	= &tsk,						\
-	.__temp_sec	= INIT_TASK_SECURITY(tsk.__temp_sec),		\
-	.sec		= &tsk.__temp_sec,				\
-	.act_as		= &tsk.__temp_sec,				\
+	.sec		= &init_task_security,				\
+	.act_as		= &init_task_security,				\
 	.comm		= "swapper",					\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
include/linux/key-ui.h +4 -6
index e8b8a7a..f15ea9d 100644
@@ -43,15 +43,13 @@ struct keyring_list {
  * check to see whether permission is granted to use a key in the desired way
  */
 extern int key_task_permission(const key_ref_t key_ref,
-			       struct task_struct *context,
+			       struct task_security *sec,
 			       key_perm_t perm);
 
-static inline int key_permission(const key_ref_t key_ref, key_perm_t perm)
-{
-	return key_task_permission(key_ref, current, perm);
-}
+#define key_permission(key_ref, perm) \
+	key_task_permission((key_ref), current->act_as, (perm))
 
-extern key_ref_t lookup_user_key(struct task_struct *context,
+extern key_ref_t lookup_user_key(struct task_security *sec,
 				 key_serial_t id, int create, int partial,
 				 key_perm_t perm);
 
include/linux/key.h +11 -20
index 163f864..ce07205 100644
@@ -70,6 +70,8 @@ struct key;
 struct seq_file;
 struct user_struct;
 struct signal_struct;
+struct task_security;
+struct thread_group_security;
 
 struct key_type;
 struct key_owner;
@@ -178,7 +180,7 @@ struct key {
 extern struct key *key_alloc(struct key_type *type,
 			     const char *desc,
 			     uid_t uid, gid_t gid,
-			     struct task_struct *ctx,
+			     struct task_security *sec,
 			     key_perm_t perm,
 			     unsigned long flags);
 
@@ -245,7 +247,7 @@ extern int key_unlink(struct key *keyring,
 		      struct key *key);
 
 extern struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid,
-				 struct task_struct *ctx,
+				 struct task_security *sec,
 				 unsigned long flags,
 				 struct key *dest);
 
@@ -267,24 +269,16 @@ extern struct key *key_lookup(key_serial_t id);
  */
 extern struct key root_user_keyring, root_session_keyring;
 extern int alloc_uid_keyring(struct user_struct *user,
-			     struct task_struct *ctx);
+			     struct task_security *sec);
 extern void switch_uid_keyring(struct user_struct *new_user);
-extern int copy_keys(unsigned long clone_flags, struct task_struct *tsk);
-extern int copy_thread_group_keys(struct task_struct *tsk);
-extern void exit_keys(struct task_struct *tsk);
-extern void exit_thread_group_keys(struct signal_struct *tg);
+extern int copy_thread_group_keys(struct thread_group_security *tgsec);
 extern int suid_keys(struct task_struct *tsk);
 extern int exec_keys(struct task_struct *tsk);
-extern void key_fsuid_changed(struct task_struct *tsk);
-extern void key_fsgid_changed(struct task_struct *tsk);
+extern void key_fsuid_changed(struct task_security *sec);
+extern void key_fsgid_changed(struct task_security *sec);
 extern void key_init(void);
-
-#define __install_session_keyring(tsk, keyring)			\
-({								\
-	struct key *old_session = tsk->signal->session_keyring;	\
-	tsk->signal->session_keyring = keyring;			\
-	old_session;						\
-})
+extern void __install_session_keyring(struct task_struct *tsk,
+				      struct key *keyring);
 
 #else /* CONFIG_KEYS */
 
@@ -298,11 +292,8 @@ extern void key_init(void);
 #define is_key_possessed(k)		0
 #define alloc_uid_keyring(u,c)		0
 #define switch_uid_keyring(u)		do { } while(0)
-#define __install_session_keyring(t, k)	({ NULL; })
-#define copy_keys(f,t)			0
+#define __install_session_keyring(t, k)	do {} while (0)
 #define copy_thread_group_keys(t)	0
-#define exit_keys(t)			do { } while(0)
-#define exit_thread_group_keys(tg)	do { } while(0)
 #define suid_keys(t)			do { } while(0)
 #define exec_keys(t)			do { } while(0)
 #define key_fsuid_changed(t)		do { } while(0)
include/linux/sched.h +33 -7
index 33afa37..2bbdf85 100644
@@ -525,12 +525,6 @@ struct signal_struct {
 
 	struct list_head cpu_timers[3];
 
-	/* keep the process-shared keyrings here so that they do the right
-	 * thing in threads created with CLONE_THREAD */
-#ifdef CONFIG_KEYS
-	struct key *session_keyring;	/* keyring inherited over fork */
-	struct key *process_keyring;	/* keyring private to this process */
-#endif
 #ifdef CONFIG_BSD_PROCESS_ACCT
 	struct pacct_struct pacct;	/* per-process accounting information */
 #endif
@@ -608,6 +602,20 @@ extern struct user_struct root_user;
 
 
 /*
+ * The common security details for a thread group
+ * - shared by CLONE_THREAD
+ */
+#ifdef CONFIG_KEYS
+struct thread_group_security {
+	atomic_t	usage;
+	pid_t		tgid;			/* thread group process ID */
+	spinlock_t	lock;
+	struct key	*session_keyring;	/* keyring inherited over fork */
+	struct key	*process_keyring;	/* keyring private to this process */
+};
+#endif
+
+/*
  * The security context of a task
  *
  * The parts of the context break down into two categories:
@@ -650,6 +658,7 @@ struct task_security {
 					 * keys to */
 	struct key	*thread_keyring; /* keyring private to this thread */
 	struct key	*request_key_auth; /* assumed request_key authority */
+	struct thread_group_security *tgsec;
 #endif
 #ifdef CONFIG_SECURITY
 	void		*security;	/* subjective LSM security */
@@ -659,10 +668,28 @@ struct task_security {
 	spinlock_t	lock;		/* lock for pointer changes */
 };
 
+extern struct task_security *dup_task_security(struct task_security *);
+extern int copy_task_security(struct task_struct *, unsigned long);
+extern void put_task_security(struct task_security *);
+
 #define current_fsuid() (current->act_as->fsuid)
 #define current_fsgid() (current->act_as->fsgid)
 #define current_cap()	(current->act_as->cap_effective)
 
+/**
+ * get_task_security - Get an extra reference on a task security record
+ * @sec: The security record to get the reference on
+ *
+ * Get an extra reference on a task security record.  The caller must arrange
+ * for this to be released.
+ */
+static inline
+struct task_security *get_task_security(struct task_security *sec)
+{
+	atomic_inc(&sec->usage);
+	return sec;
+}
+
 
 struct backing_dev_info;
 struct reclaim_state;
@@ -1155,7 +1182,6 @@ struct task_struct {
 	struct list_head cpu_timers[3];
 
 /* process credentials */
-	struct task_security __temp_sec __deprecated; /* temporary security to be removed */
 	struct task_security *sec;	/* actual/objective task security */
 	struct task_security *act_as;	/* effective/subjective task security */
 
include/linux/security.h +29 -14

113 lines not on this page · raw message

kernel/Makefile +1 -1
index 685697c..afc1da1 100644
@@ -8,7 +8,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
-	    hrtimer.o rwsem.o nsproxy.o srcu.o \
+	    hrtimer.o rwsem.o nsproxy.o srcu.o cred.o \
 	    utsname.o notifier.o ksysfs.o pm_qos_params.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_check.o
kernel/cred.c new file +140 -0

140 lines not on this page · raw message

kernel/exit.c +0 -1
index 910c793..e94b5ab 100644
@@ -998,7 +998,6 @@ fastcall NORET_TYPE void do_exit(long code)
 	check_stack_usage();
 	exit_thread();
 	cgroup_exit(tsk, 1);
-	exit_keys(tsk);
 
 	if (group_dead && tsk->signal->leader)
 		disassociate_ctty(1);
kernel/fork.c +12 -28
index 6580020..0c655b6 100644
@@ -123,9 +123,8 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
-	security_task_free(tsk);
-	free_uid(tsk->__temp_sec.user);
-	put_group_info(tsk->__temp_sec.group_info);
+	put_task_security(tsk->sec);
+	put_task_security(tsk->act_as);
 	delayacct_tsk_free(tsk);
 
 	if (!profile_handoff_task(tsk))
@@ -877,7 +876,6 @@ void __cleanup_sighand(struct sighand_struct *sighand)
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
-	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
 		atomic_inc(&current->signal->count);
@@ -889,12 +887,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	if (!sig)
 		return -ENOMEM;
 
-	ret = copy_thread_group_keys(tsk);
-	if (ret < 0) {
-		kmem_cache_free(signal_cachep, sig);
-		return ret;
-	}
-
 	atomic_set(&sig->count, 1);
 	atomic_set(&sig->live, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
@@ -952,7 +944,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_signal(struct signal_struct *sig)
 {
-	exit_thread_group_keys(sig);
 	kmem_cache_free(signal_cachep, sig);
 }
 
@@ -1046,18 +1037,19 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
-	p->act_as = p->sec = &p->__temp_sec;
+	retval = copy_task_security(p, clone_flags);
+	if (retval < 0)
+		goto bad_fork_free;
+
 	retval = -EAGAIN;
 	if (atomic_read(&p->sec->user->processes) >=
 			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
 		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
 		    p->sec->user != current->nsproxy->user_ns->root_user)
-			goto bad_fork_free;
+			goto bad_fork_cleanup_put_task_sec;
 	}
 
-	atomic_inc(&p->sec->user->__count);
 	atomic_inc(&p->sec->user->processes);
-	get_group_info(p->sec->group_info);
 
 	/*
 	 * If multiple threads are within copy_process(), then this check
@@ -1121,9 +1113,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	do_posix_clock_monotonic_gettime(&p->start_time);
 	p->real_start_time = p->start_time;
 	monotonic_to_bootbased(&p->real_start_time);
-#ifdef CONFIG_SECURITY
-	p->sec->security = NULL;
-#endif
 	p->io_context = NULL;
 	p->audit_context = NULL;
 	cgroup_fork(p);
@@ -1171,7 +1160,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if ((retval = security_task_alloc(p)))
 		goto bad_fork_cleanup_policy;
 	if ((retval = audit_alloc(p)))
-		goto bad_fork_cleanup_security;
+		goto bad_fork_cleanup_policy;
 	/* copy all the process information */
 	if ((retval = copy_semundo(clone_flags, p)))
 		goto bad_fork_cleanup_audit;
@@ -1185,10 +1174,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_sighand;
 	if ((retval = copy_mm(clone_flags, p)))
 		goto bad_fork_cleanup_signal;
-	if ((retval = copy_keys(clone_flags, p)))
-		goto bad_fork_cleanup_mm;
 	if ((retval = copy_namespaces(clone_flags, p)))
-		goto bad_fork_cleanup_keys;
+		goto bad_fork_cleanup_mm;
 	if ((retval = copy_io(clone_flags, p)))
 		goto bad_fork_cleanup_namespaces;
 	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
@@ -1364,8 +1351,6 @@ bad_fork_cleanup_io:
 	put_io_context(p->io_context);
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
-bad_fork_cleanup_keys:
-	exit_keys(p);
 bad_fork_cleanup_mm:
 	if (p->mm)
 		mmput(p->mm);
@@ -1381,8 +1366,6 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_security:
-	security_task_free(p);
 bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_free(p->mempolicy);
@@ -1395,9 +1378,10 @@ bad_fork_cleanup_cgroup:
 bad_fork_cleanup_put_domain:
 	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
-	put_group_info(p->sec->group_info);
 	atomic_dec(&p->sec->user->processes);
-	free_uid(p->sec->user);
+bad_fork_cleanup_put_task_sec:
+	put_task_security(p->act_as);
+	put_task_security(p->sec);
 bad_fork_free:
 	free_task(p);
 fork_out:
kernel/kmod.c +4 -6
index bb7df2a..7476b5f 100644
@@ -133,20 +133,18 @@ struct subprocess_info {
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
-	struct key *new_session, *old_session;
 	int retval;
 
-	/* Unblock all signals and set the session keyring. */
-	new_session = key_get(sub_info->ring);
+	/* Set the session keyring. */
+	__install_session_keyring(current, sub_info->ring);
+
+	/* Unblock all signals. */
 	spin_lock_irq(&current->sighand->siglock);
-	old_session = __install_session_keyring(current, new_session);
 	flush_signal_handlers(current, 1);
 	sigemptyset(&current->blocked);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	key_put(old_session);
-
 	/* Install input pipe when needed */
 	if (sub_info->stdin) {
 		struct files_struct *f = current->files;
kernel/sys.c +8 -8
index b956bfe..f5d33f2 100644
@@ -521,7 +521,7 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
 	sec->fsgid = new_egid;
 	sec->egid = new_egid;
 	sec->gid = new_rgid;
-	key_fsgid_changed(current);
+	key_fsgid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_GID);
 	return 0;
 }
@@ -557,7 +557,7 @@ asmlinkage long sys_setgid(gid_t gid)
 	else
 		return -EPERM;
 
-	key_fsgid_changed(current);
+	key_fsgid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_GID);
 	return 0;
 }
@@ -646,7 +646,7 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 		sec->suid = sec->euid;
 	sec->fsuid = sec->euid;
 
-	key_fsuid_changed(current);
+	key_fsuid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_UID);
 
 	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
@@ -694,7 +694,7 @@ asmlinkage long sys_setuid(uid_t uid)
 	sec->fsuid = sec->euid = uid;
 	sec->suid = new_suid;
 
-	key_fsuid_changed(current);
+	key_fsuid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_UID);
 
 	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
@@ -744,7 +744,7 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if (suid != (uid_t) -1)
 		sec->suid = suid;
 
-	key_fsuid_changed(current);
+	key_fsuid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_UID);
 
 	return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
@@ -798,7 +798,7 @@ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 	if (sgid != (gid_t) -1)
 		sec->sgid = sgid;
 
-	key_fsgid_changed(current);
+	key_fsgid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_GID);
 	return 0;
 }
@@ -841,7 +841,7 @@ asmlinkage long sys_setfsuid(uid_t uid)
 		sec->fsuid = uid;
 	}
 
-	key_fsuid_changed(current);
+	key_fsuid_changed(sec);
 	proc_id_connector(current, PROC_EVENT_UID);
 
 	security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
@@ -869,7 +869,7 @@ asmlinkage long sys_setfsgid(gid_t gid)
 			smp_wmb();
 		}
 		sec->fsgid = gid;
-		key_fsgid_changed(current);
+		key_fsgid_changed(sec);
 		proc_id_connector(current, PROC_EVENT_GID);
 	}
 	return old_fsgid;
kernel/user.c +1 -1
index 3a2151d..0fa3a39 100644
@@ -349,7 +349,7 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
 #endif
 		new->locked_shm = 0;
 
-		if (alloc_uid_keyring(new, current) < 0)
+		if (alloc_uid_keyring(new, current->sec) < 0)
 			goto out_free_user;
 
 		if (sched_create_user(new) < 0)
net/rxrpc/ar-key.c +2 -2
index 9a8ff68..14979a5 100644
@@ -297,7 +297,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn,
 
 	_enter("");
 
-	key = key_alloc(&key_type_rxrpc, "x", 0, 0, current, 0,
+	key = key_alloc(&key_type_rxrpc, "x", 0, 0, current->act_as, 0,
 			KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(key)) {
 		_leave(" = -ENOMEM [alloc %ld]", PTR_ERR(key));
@@ -343,7 +343,7 @@ struct key *rxrpc_get_null_key(const char *keyname)
 	struct key *key;
 	int ret;
 
-	key = key_alloc(&key_type_rxrpc, keyname, 0, 0, current,
+	key = key_alloc(&key_type_rxrpc, keyname, 0, 0, current->act_as,
 			KEY_POS_SEARCH, KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(key))
 		return key;
security/dummy.c +10 -4
index 28413ae..cc516ab 100644
@@ -503,16 +503,21 @@ static int dummy_task_create (unsigned long clone_flags)
 	return 0;
 }
 
-static int dummy_task_alloc_security (struct task_struct *p)
+static int dummy_task_alloc_security(struct task_struct *p)
 {
 	return 0;
 }
 
-static void dummy_task_free_security (struct task_struct *p)
+static void dummy_task_free_security(struct task_security *sec)
 {
 	return;
 }
 
+static int dummy_task_dup_security(struct task_security *p)
+{
+	return 0;
+}
+
 static int dummy_task_setuid (uid_t id0, uid_t id1, uid_t id2, int flags)
 {
 	return 0;
@@ -971,7 +976,7 @@ static void dummy_release_secctx(char *secdata, u32 seclen)
 }
 
 #ifdef CONFIG_KEYS
-static inline int dummy_key_alloc(struct key *key, struct task_struct *ctx,
+static inline int dummy_key_alloc(struct key *key, struct task_security *sec,
 				  unsigned long flags)
 {
 	return 0;
@@ -982,7 +987,7 @@ static inline void dummy_key_free(struct key *key)
 }
 
 static inline int dummy_key_permission(key_ref_t key_ref,
-				       struct task_struct *context,
+				       struct task_security *sec,
 				       key_perm_t perm)
 {
 	return 0;
@@ -1087,6 +1092,7 @@ void security_fixup_ops (struct security_operations *ops)
 	set_to_dummy_if_null(ops, task_create);
 	set_to_dummy_if_null(ops, task_alloc_security);
 	set_to_dummy_if_null(ops, task_free_security);
+	set_to_dummy_if_null(ops, task_dup_security);
 	set_to_dummy_if_null(ops, task_setuid);
 	set_to_dummy_if_null(ops, task_post_setuid);
 	set_to_dummy_if_null(ops, task_setgid);
security/keys/internal.h +5 -5
index f004835..a439889 100644
@@ -92,7 +92,7 @@ extern struct key *keyring_search_instkey(struct key *keyring,
 typedef int (*key_match_func_t)(const struct key *, const void *);
 
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-				    struct task_struct *tsk,
+				    struct task_security *sec,
 				    struct key_type *type,
 				    const void *description,
 				    key_match_func_t match);
@@ -100,12 +100,12 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 extern key_ref_t search_process_keyrings(struct key_type *type,
 					 const void *description,
 					 key_match_func_t match,
-					 struct task_struct *tsk);
+					 struct task_security *sec);
 
 extern struct key *find_keyring_by_name(const char *name, key_serial_t bound);
 
-extern int install_thread_keyring(struct task_struct *tsk);
-extern int install_process_keyring(struct task_struct *tsk);
+extern int install_thread_keyring(struct task_security *sec);
+extern int install_process_keyring(struct task_security *sec);
 
 extern struct key *request_key_and_link(struct key_type *type,
 					const char *description,
@@ -120,7 +120,7 @@ extern struct key *request_key_and_link(struct key_type *type,
  */
 struct request_key_auth {
 	struct key		*target_key;
-	struct task_struct	*context;
+	struct task_security	*sec;
 	void			*callout_info;
 	size_t			callout_len;
 	pid_t			pid;
security/keys/key.c +3 -3
index 4d1a253..f6ca221 100644
@@ -243,7 +243,7 @@ serial_exists:
  *   instantiate the key or discard it before returning
  */
 struct key *key_alloc(struct key_type *type, const char *desc,
-		      uid_t uid, gid_t gid, struct task_struct *ctx,
+		      uid_t uid, gid_t gid, struct task_security *sec,
 		      key_perm_t perm, unsigned long flags)
 {
 	struct key_user *user = NULL;
@@ -314,7 +314,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 #endif
 
 	/* let the security module know about the key */
-	ret = security_key_alloc(key, ctx, flags);
+	ret = security_key_alloc(key, sec, flags);
 	if (ret < 0)
 		goto security_error;
 
@@ -818,7 +818,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 
 	/* allocate a new key */
 	key = key_alloc(ktype, description, current_fsuid(), current_fsgid(),
-			current, perm, flags);
+			current->act_as, perm, flags);
 	if (IS_ERR(key)) {
 		key_ref = ERR_CAST(key);
 		goto error_3;
security/keys/keyctl.c +3 -3
index 4051948..2900451 100644
@@ -878,7 +878,7 @@ long keyctl_instantiate_key(key_serial_t id,
 	 * requesting task */
 	keyring_ref = NULL;
 	if (ringid) {
-		keyring_ref = lookup_user_key(rka->context, ringid, 1, 0,
+		keyring_ref = lookup_user_key(rka->sec, ringid, 1, 0,
 					      KEY_WRITE);
 		if (IS_ERR(keyring_ref)) {
 			ret = PTR_ERR(keyring_ref);
@@ -973,13 +973,13 @@ long keyctl_set_reqkey_keyring(int reqkey_defl)
 
 	switch (reqkey_defl) {
 	case KEY_REQKEY_DEFL_THREAD_KEYRING:
-		ret = install_thread_keyring(current);
+		ret = install_thread_keyring(sec);
 		if (ret < 0)
 			return ret;
 		goto set;
 
 	case KEY_REQKEY_DEFL_PROCESS_KEYRING:
-		ret = install_process_keyring(current);
+		ret = install_process_keyring(sec);
 		if (ret < 0)
 			return ret;
 
security/keys/keyring.c +7 -7
index 76b89b2..6ccd8f8 100644
@@ -244,14 +244,14 @@ static long keyring_read(const struct key *keyring,
  * allocate a keyring and link into the destination keyring
  */
 struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid,
-			  struct task_struct *ctx, unsigned long flags,
+			  struct task_security *sec, unsigned long flags,
 			  struct key *dest)
 {
 	struct key *keyring;
 	int ret;
 
 	keyring = key_alloc(&key_type_keyring, description,
-			    uid, gid, ctx,
+			    uid, gid, sec,
 			    (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL,
 			    flags);
 
@@ -280,7 +280,7 @@ struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid,
  * - we propagate the possession attribute from the keyring ref to the key ref
  */
 key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-			     struct task_struct *context,
+			     struct task_security *sec,
 			     struct key_type *type,
 			     const void *description,
 			     key_match_func_t match)
@@ -303,7 +303,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	key_check(keyring);
 
 	/* top keyring must have search permission to begin the search */
-        err = key_task_permission(keyring_ref, context, KEY_SEARCH);
+	err = key_task_permission(keyring_ref, sec, KEY_SEARCH);
 	if (err < 0) {
 		key_ref = ERR_PTR(err);
 		goto error;
@@ -376,7 +376,7 @@ descend:
 
 		/* key must have search permissions */
 		if (key_task_permission(make_key_ref(key, possessed),
-					context, KEY_SEARCH) < 0)
+					sec, KEY_SEARCH) < 0)
 			continue;
 
 		/* we set a different error code if we pass a negative key */
@@ -403,7 +403,7 @@ ascend:
 			continue;
 
 		if (key_task_permission(make_key_ref(key, possessed),
-					context, KEY_SEARCH) < 0)
+					sec, KEY_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
@@ -458,7 +458,7 @@ key_ref_t keyring_search(key_ref_t keyring,
 	if (!type->match)
 		return ERR_PTR(-ENOKEY);
 
-	return keyring_search_aux(keyring, current,
+	return keyring_search_aux(keyring, current->sec,
 				  type, description, type->match);
 
 } /* end keyring_search() */
security/keys/permission.c +2 -3
index 07898bd..eff3e29 100644
@@ -19,10 +19,9 @@
  * but permit the security modules to override
  */
 int key_task_permission(const key_ref_t key_ref,
-			struct task_struct *context,
+			struct task_security *sec,
 			key_perm_t perm)
 {
-	struct task_security *sec = context->act_as;
 	struct key *key;
 	key_perm_t kperm;
 	int ret;
@@ -69,7 +68,7 @@ use_these_perms:
 		return -EACCES;
 
 	/* let LSM be the final arbiter */
-	return security_key_permission(key_ref, context, perm);
+	return security_key_permission(key_ref, sec, perm);
 
 } /* end key_task_permission() */
 
security/keys/proc.c +1 -1
index 6941260..d83d5b5 100644
@@ -141,7 +141,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 
 	/* check whether the current task is allowed to view the key (assuming
 	 * non-possession) */
-	rc = key_task_permission(make_key_ref(key, 0), current, KEY_VIEW);
+	rc = key_task_permission(make_key_ref(key, 0), current->sec, KEY_VIEW);
 	if (rc < 0)
 		return 0;
 
security/keys/process_keys.c +133 -157

585 lines not on this page · raw message

security/keys/request_key.c +28 -31

174 lines not on this page · raw message

security/keys/request_key_auth.c +15 -23
index d306412..2513d90 100644
@@ -104,10 +104,8 @@ static void request_key_auth_revoke(struct key *key)
 
 	kenter("{%d}", key->serial);
 
-	if (rka->context) {
-		put_task_struct(rka->context);
-		rka->context = NULL;
-	}
+	put_task_security(rka->sec);
+	rka->sec = NULL;
 
 } /* end request_key_auth_revoke() */
 
@@ -121,11 +119,7 @@ static void request_key_auth_destroy(struct key *key)
 
 	kenter("{%d}", key->serial);
 
-	if (rka->context) {
-		put_task_struct(rka->context);
-		rka->context = NULL;
-	}
-
+	put_task_security(rka->sec);
 	key_put(rka->target_key);
 	kfree(rka->callout_info);
 	kfree(rka);
@@ -141,6 +135,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info,
 				 size_t callout_len)
 {
 	struct request_key_auth *rka, *irka;
+	struct task_security *sec = current->sec;
 	struct key *authkey = NULL;
 	char desc[20];
 	int ret;
@@ -162,28 +157,25 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info,
 
 	/* see if the calling process is already servicing the key request of
 	 * another process */
-	if (current->act_as->request_key_auth) {
+	if (sec->request_key_auth) {
 		/* it is - use that instantiation context here too */
-		down_read(&current->act_as->request_key_auth->sem);
+		down_read(&sec->request_key_auth->sem);
 
 		/* if the auth key has been revoked, then the key we're
 		 * servicing is already instantiated */
-		if (test_bit(KEY_FLAG_REVOKED,
-			     &current->act_as->request_key_auth->flags))
+		if (test_bit(KEY_FLAG_REVOKED, &sec->request_key_auth->flags))
 			goto auth_key_revoked;
 
-		irka = current->act_as->request_key_auth->payload.data;
-		rka->context = irka->context;
+		irka = sec->request_key_auth->payload.data;
+		rka->sec = irka->sec;
 		rka->pid = irka->pid;
-		get_task_struct(rka->context);
+		get_task_security(rka->sec);
 
-		up_read(&current->act_as->request_key_auth->sem);
-	}
-	else {
+		up_read(&sec->request_key_auth->sem);
+	} else {
 		/* it isn't - use this process as the context */
-		rka->context = current;
+		rka->sec = get_task_security(sec);
 		rka->pid = current->pid;
-		get_task_struct(rka->context);
 	}
 
 	rka->target_key = key_get(target);
@@ -194,7 +186,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info,
 	sprintf(desc, "%x", target->serial);
 
 	authkey = key_alloc(&key_type_request_key_auth, desc,
-			    current_fsuid(), current_fsgid(), current,
+			    sec->fsuid, sec->fsgid, sec,
 			    KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH |
 			    KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(authkey)) {
@@ -260,7 +252,7 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id)
 		&key_type_request_key_auth,
 		(void *) (unsigned long) target_id,
 		key_get_instantiation_authkey_match,
-		current);
+		current->act_as);
 
 	if (IS_ERR(authkey_ref)) {
 		authkey = ERR_CAST(authkey_ref);
security/security.c +13 -7
index 3e75b90..3aceeac 100644
@@ -590,9 +590,14 @@ int security_task_alloc(struct task_struct *p)
 	return security_ops->task_alloc_security(p);
 }
 
-void security_task_free(struct task_struct *p)
+void security_task_free(struct task_security *sec)
 {
-	security_ops->task_free_security(p);
+	security_ops->task_free_security(sec);
+}
+
+int security_task_dup(struct task_security *sec)
+{
+	return security_ops->task_dup_security(sec);
 }
 
 int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags)
@@ -1086,9 +1091,10 @@ EXPORT_SYMBOL(security_skb_classify_flow);
 
 #ifdef CONFIG_KEYS
 
-int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long flags)
+int security_key_alloc(struct key *key, struct task_security *sec,
+		       unsigned long flags)
 {
-	return security_ops->key_alloc(key, tsk, flags);
+	return security_ops->key_alloc(key, sec, flags);
 }
 
 void security_key_free(struct key *key)
@@ -1096,10 +1102,10 @@ void security_key_free(struct key *key)
 	security_ops->key_free(key);
 }
 
-int security_key_permission(key_ref_t key_ref,
-			    struct task_struct *context, key_perm_t perm)
+int security_key_permission(key_ref_t key_ref, struct task_security *sec,
+			    key_perm_t perm)
 {
-	return security_ops->key_permission(key_ref, context, perm);
+	return security_ops->key_permission(key_ref, sec, perm);
 }
 
 int security_key_getsecurity(struct key *key, char **_buffer)
security/selinux/hooks.c +35 -11

92 lines not on this page · raw message

maintainer
#10 lore raw

Re: [PATCH 07/37] Security: De-embed task security record from task and use refcounting

Quoted 3 lines · David Howells

Remove the temporarily embedded task security record from task_struct. Instead it is made to dangle from the task_struct::sec and task_struct::act_as pointers with references counted for each.

...

These patches are kind of huge.

Quoted 12 lines
security/selinux/hooks.c +12 -0
+static int selinux_task_dup_security(struct task_security *sec)
+{
+	struct task_security_struct *tsec1, *tsec2;
+
+	tsec1 = sec->security;
+
+	tsec2 = kmemdup(tsec1, sizeof(*tsec1), GFP_KERNEL);
+	if (!tsec2)
+		return -ENOMEM;
+
+	tsec2->osid = tsec1->osid;
+	tsec2->sid = tsec1->sid;

security/selinux/hooks.c static int selinux_task_alloc_security(struct task_struct *tsk) · line 3093

Quoted 10 lines
security/selinux/hooks.c +9 -0
+
+	tsec2->exec_sid = tsec1->exec_sid;
+	tsec2->create_sid = tsec1->create_sid;
+	tsec2->keycreate_sid = tsec1->keycreate_sid;
+	tsec2->sockcreate_sid = tsec1->sockcreate_sid;
+	tsec2->ptrace_sid = SECINITSID_UNLABELED;
+	sec->security = tsec2;
+
+	return 0;
 }

Why manually copy these fields after a kmemdup?

What about the task backpointer? (i.e. tsec2->task)

Signature · 2 lines
James Morris
<[email protected]>
author maintainer
#11 lore raw

Re: [PATCH 07/37] Security: De-embed task security record from task and use refcounting

Quoted 7 lines · James Morris
Quoted 3 lines

Remove the temporarily embedded task security record from task_struct. Instead it is made to dangle from the task_struct::sec and task_struct::act_as pointers with references counted for each.

...

These patches are kind of huge.

Yeah, I know. The problem is that each patch must compile and run. They can't be split up without violating that unfortunately.

Quoted 1 line

Why manually copy these fields after a kmemdup?

Fair point. Fixed.

Quoted 1 line

What about the task backpointer? (i.e. tsec2->task)

The problem is that there can't be one with this patch as the task_security struct and the LSM security data attached to it may outlive the task it points back to.

It seems that the backpointer can be dispensed with. Nothing particularly seems to use it. Do you know the reason for its existence?

David

#12 lore raw

Re: [PATCH 07/37] Security: De-embed task security record from task and use refcounting

Quoted 17 lines · David Howells
Quoted 7 lines · James Morris
Quoted 3 lines

Remove the temporarily embedded task security record from task_struct. Instead it is made to dangle from the task_struct::sec and task_struct::act_as pointers with references counted for each.

...

These patches are kind of huge.

Yeah, I know. The problem is that each patch must compile and run. They can't be split up without violating that unfortunately.

Quoted 1 line

Why manually copy these fields after a kmemdup?

Fair point. Fixed.

Quoted 8 lines
Quoted 1 line

What about the task backpointer? (i.e. tsec2->task)

The problem is that there can't be one with this patch as the task_security struct and the LSM security data attached to it may outlive the task it points back to.

It seems that the backpointer can be dispensed with. Nothing particularly seems to use it. Do you know the reason for its existence?

Looks unused now.
Similarly for some of the other security structs.
Only inode, superblock, and sock back pointers still seem to be in use.

Signature · 8 lines
Stephen Smalley
National Security Agency


--
This message was distributed to subscribers of the selinux mailing list.
If you no longer wish to subscribe, send mail to [email protected] with
the words "unsubscribe selinux" without quotes as the message.
author maintainer
#13 lore raw

PATCH 8/37 Security: Add a kernel_service object class to SELinux

In reply to David Howells

Add a 'kernel_service' object class to SELinux and give this object class two access vectors: 'use_as_override' and 'create_files_as'.

The first vector is used to grant a process the right to nominate an alternate process security ID for the kernel to use as an override for the SELinux subjective security when accessing stuff on behalf of another process.

For example, CacheFiles when accessing the cache on behalf on a process accessing an NFS file needs to use a subjective security ID appropriate to the cache rather then the one the calling process is using. The cachefilesd daemon will nominate the security ID to be used.

The second vector is used to grant a process the right to nominate a file creation label for a kernel service to use.

---

 security/selinux/include/av_perm_to_string.h |    2 ++
 security/selinux/include/av_permissions.h    |    2 ++
 security/selinux/include/class_to_string.h   |    1 +
 security/selinux/include/flask.h             |    1 +
 4 files changed, 6 insertions(+), 0 deletions(-)
security/selinux/include/av_perm_to_string.h +2 -0
index 399f868..c68ec9c 100644
@@ -168,3 +168,5 @@
    S_(SECCLASS_DCCP_SOCKET, DCCP_SOCKET__NAME_CONNECT, "name_connect")
    S_(SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, "mmap_zero")
    S_(SECCLASS_PEER, PEER__RECV, "recv")
+   S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, "use_as_override")
+   S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, "create_files_as")
security/selinux/include/av_permissions.h +2 -0
index 84c9abc..41cee9e 100644
@@ -833,3 +833,5 @@
 #define DCCP_SOCKET__NAME_CONNECT                 0x00800000UL
 #define MEMPROTECT__MMAP_ZERO                     0x00000001UL
 #define PEER__RECV                                0x00000001UL
+#define KERNEL_SERVICE__USE_AS_OVERRIDE           0x00000001UL
+#define KERNEL_SERVICE__CREATE_FILES_AS           0x00000002UL
security/selinux/include/class_to_string.h +1 -0
index b1b0d1d..efe9efa 100644
@@ -71,3 +71,4 @@
     S_(NULL)
     S_(NULL)
     S_("peer")
+    S_("kernel_service")
security/selinux/include/flask.h +1 -0
index 09e9dd2..2bc251a 100644
@@ -51,6 +51,7 @@
 #define SECCLASS_DCCP_SOCKET                             60
 #define SECCLASS_MEMPROTECT                              61
 #define SECCLASS_PEER                                    68
+#define SECCLASS_KERNEL_SERVICE                          69
 
 /*
  * Security identifier indices for initial entities

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

maintainer
#14 lore raw

Re: [PATCH 08/37] Security: Add a kernel_service object class to SELinux

security/selinux/include/flask.h line 54

Quoted 6 lines · David Howells

+++ b/security/selinux/include/flask.h

security/selinux/include/flask.h +1 -0
@@ -51,6 +51,7 @@
 #define SECCLASS_DCCP_SOCKET                             60
 #define SECCLASS_MEMPROTECT                              61
 #define SECCLASS_PEER                                    68
+#define SECCLASS_KERNEL_SERVICE                          69

I just pushed a patch to Linus from Stephen which uses this class number; you'll likely need to bump it to 70.

Signature · 2 lines
James Morris
<[email protected]>
author maintainer
#15 lore raw

PATCH 9/37 Security: Allow kernel services to override LSM settings for task actions

In reply to David Howells

Allow kernel services to override LSM settings appropriate to the actions performed by a task by duplicating a security record, modifying it and then using task_struct::act_as to point to it when performing operations on behalf of a task.

This is used, for example, by CacheFiles which has to transparently access the cache on behalf of a process that thinks it is doing, say, NFS accesses with a potentially inappropriate (with respect to accessing the cache) set of security data.

This patch provides two LSM hooks for modifying a task security record:

(*) security_kernel_act_as() which allows modification of the security datum
with which a task acts on other objects (most notably files).

(*) security_create_files_as() which allows modification of the security
datum that is used to initialise the security data on a file that a task creates.

---

 include/linux/capability.h          |   12 ++--
 include/linux/cred.h                |   23 +++++++
 include/linux/security.h            |   43 +++++++++++++
 kernel/cred.c                       |  112 +++++++++++++++++++++++++++++++++++
 security/dummy.c                    |   17 +++++
 security/security.c                 |   15 ++++-
 security/selinux/hooks.c            |   51 ++++++++++++++++
 security/selinux/include/security.h |    2 -
 security/selinux/ss/services.c      |    5 +-
 9 files changed, 265 insertions(+), 15 deletions(-)
 create mode 100644 include/linux/cred.h
include/linux/capability.h +6 -6
index 7d50ff6..424de01 100644
@@ -364,12 +364,12 @@ typedef struct kernel_cap_struct {
 # error Fix up hand-coded capability macro initializers
 #else /* HAND-CODED capability initializers */
 
-# define CAP_EMPTY_SET    {{ 0, 0 }}
-# define CAP_FULL_SET     {{ ~0, ~0 }}
-# define CAP_INIT_EFF_SET {{ ~CAP_TO_MASK(CAP_SETPCAP), ~0 }}
-# define CAP_FS_SET       {{ CAP_FS_MASK_B0, CAP_FS_MASK_B1 } }
-# define CAP_NFSD_SET     {{ CAP_FS_MASK_B0|CAP_TO_MASK(CAP_SYS_RESOURCE), \
-			     CAP_FS_MASK_B1 } }
+# define CAP_EMPTY_SET    ((kernel_cap_t){{ 0, 0 }})
+# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, ~0 }})
+# define CAP_INIT_EFF_SET ((kernel_cap_t){{ ~CAP_TO_MASK(CAP_SETPCAP), ~0 }})
+# define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0, CAP_FS_MASK_B1 } })
+# define CAP_NFSD_SET     ((kernel_cap_t){{ CAP_FS_MASK_B0|CAP_TO_MASK(CAP_SYS_RESOURCE), \
+					CAP_FS_MASK_B1 } })
 
 #endif /* _LINUX_CAPABILITY_U32S != 2 */
 
include/linux/cred.h new file +23 -0
new file mode 100644
index 0000000..497af5b
@@ -0,0 +1,23 @@
+/* Credential management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_CRED_H
+#define _LINUX_CRED_H
+
+struct task_security;
+struct inode;
+
+extern struct task_security *get_kernel_security(struct task_struct *);
+extern int set_security_override(struct task_security *, u32);
+extern int set_security_override_from_ctx(struct task_security *, const char *);
+extern int change_create_files_as(struct task_security *, struct inode *);
+
+#endif /* _LINUX_CRED_H */
include/linux/security.h +40 -3

85 lines not on this page · raw message

kernel/cred.c +112 -0

121 lines not on this page · raw message

security/dummy.c +16 -1
index cc516ab..965504a 100644
@@ -518,6 +518,19 @@ static int dummy_task_dup_security(struct task_security *p)
 	return 0;
 }
 
+static int dummy_task_kernel_act_as(struct task_struct *p,
+				    struct task_security *sec, u32 secid)
+{
+	return 0;
+}
+
+static int dummy_task_create_files_as(struct task_struct *p,
+				      struct task_security *sec,
+				      struct inode *inode)
+{
+	return 0;
+}
+
 static int dummy_task_setuid (uid_t id0, uid_t id1, uid_t id2, int flags)
 {
 	return 0;
@@ -966,7 +979,7 @@ static int dummy_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 	return -EOPNOTSUPP;
 }
 
-static int dummy_secctx_to_secid(char *secdata, u32 seclen, u32 *secid)
+static int dummy_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
 	return -EOPNOTSUPP;
 }
@@ -1093,6 +1106,8 @@ void security_fixup_ops (struct security_operations *ops)
 	set_to_dummy_if_null(ops, task_alloc_security);
 	set_to_dummy_if_null(ops, task_free_security);
 	set_to_dummy_if_null(ops, task_dup_security);
+	set_to_dummy_if_null(ops, task_kernel_act_as);
+	set_to_dummy_if_null(ops, task_create_files_as);
 	set_to_dummy_if_null(ops, task_setuid);
 	set_to_dummy_if_null(ops, task_post_setuid);
 	set_to_dummy_if_null(ops, task_setgid);
security/security.c +14 -1
index 3aceeac..e7345e1 100644
@@ -600,6 +600,19 @@ int security_task_dup(struct task_security *sec)
 	return security_ops->task_dup_security(sec);
 }
 
+int security_task_kernel_act_as(struct task_struct *p,
+				struct task_security *sec, u32 secid)
+{
+	return security_ops->task_kernel_act_as(p, sec, secid);
+}
+
+int security_task_create_files_as(struct task_struct *p,
+				  struct task_security *sec,
+				  struct inode *inode)
+{
+	return security_ops->task_create_files_as(p, sec, inode);
+}
+
 int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags)
 {
 	return security_ops->task_setuid(id0, id1, id2, flags);
@@ -838,7 +851,7 @@ int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 }
 EXPORT_SYMBOL(security_secid_to_secctx);
 
-int security_secctx_to_secid(char *secdata, u32 seclen, u32 *secid)
+int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
 	return security_ops->secctx_to_secid(secdata, seclen, secid);
 }
security/selinux/hooks.c +50 -1

69 lines not on this page · raw message

security/selinux/include/security.h +1 -1
index 837ce42..7c1e8ba 100644
@@ -78,7 +78,7 @@ int security_change_sid(u32 ssid, u32 tsid,
 int security_sid_to_context(u32 sid, char **scontext,
 	u32 *scontext_len);
 
-int security_context_to_sid(char *scontext, u32 scontext_len,
+int security_context_to_sid(const char *scontext, u32 scontext_len,
 	u32 *out_sid);
 
 int security_context_to_sid_default(char *scontext, u32 scontext_len, u32 *out_sid, u32 def_sid);
security/selinux/ss/services.c +3 -2
index f374186..519b2c1 100644
@@ -680,7 +680,8 @@ out:
 
 }
 
-static int security_context_to_sid_core(char *scontext, u32 scontext_len, u32 *sid, u32 def_sid)
+static int security_context_to_sid_core(const char *scontext, u32 scontext_len,
+					u32 *sid, u32 def_sid)
 {
 	char *scontext2;
 	struct context context;
@@ -806,7 +807,7 @@ out:
  * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
  * memory is available, or 0 on success.
  */
-int security_context_to_sid(char *scontext, u32 scontext_len, u32 *sid)
+int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid)
 {
 	return security_context_to_sid_core(scontext, scontext_len,
 	                                    sid, SECSID_NULL);
author maintainer
#16 lore raw

PATCH 10/37 Security: Make NFSD work with detached security

In reply to David Howells

Make NFSD work with detached security, using the patches that excise the security information from task_struct to struct task_security as a base.

Each time NFSD wants a new security descriptor (to do NFS4 recovery or just to do NFS operations), a task_security record is derived from NFSD's *objective* security, modified and then applied as the *subjective* security. This means
(a) the changes are not visible to anyone looking at NFSD through /proc, (b) there is no leakage between two consecutive ops with different security configurations.

Consideration should probably be given to caching the task_security record on the basis that there'll probably be several ops that will want to use any particular security configuration.

Furthermore, nfs4recover.c perhaps ought to set an appropriate LSM context on the record pointed to by rec_security so that the disk is accessed appropriately (see set_security_override[_from_ctx]()).

NOTE! This patch must be rolled in to one of the earlier security patches to make it compile fully.

---

 fs/nfsd/auth.c        |   37 +++++++++++++++++++---------
 fs/nfsd/nfs4recover.c |   64 +++++++++++++++++++++++++++++++------------------
 2 files changed, 65 insertions(+), 36 deletions(-)
fs/nfsd/auth.c +25 -12
index 5586157..ebdc562 100644
@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcauth.h>
 #include <linux/nfsd/nfsd.h>
@@ -26,12 +27,17 @@ int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
 
 int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 {
-	struct task_security *act_as = current->act_as;
+	struct task_security *sec, *old;
 	struct svc_cred	cred = rqstp->rq_cred;
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
 	int ret;
 
+	/* derive the new security record from nfsd's objective security */
+	sec = get_kernel_security(current);
+	if (!sec)
+		return -ENOMEM;
+
 	if (flags & NFSEXP_ALLSQUASH) {
 		cred.cr_uid = exp->ex_anon_uid;
 		cred.cr_gid = exp->ex_anon_gid;
@@ -55,26 +61,33 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 		get_group_info(cred.cr_group_info);
 
 	if (cred.cr_uid != (uid_t) -1)
-		act_as->fsuid = cred.cr_uid;
+		sec->fsuid = cred.cr_uid;
 	else
-		act_as->fsuid = exp->ex_anon_uid;
+		sec->fsuid = exp->ex_anon_uid;
 	if (cred.cr_gid != (gid_t) -1)
-		act_as->fsgid = cred.cr_gid;
+		sec->fsgid = cred.cr_gid;
 	else
-		act_as->fsgid = exp->ex_anon_gid;
+		sec->fsgid = exp->ex_anon_gid;
 
-	if (!cred.cr_group_info)
+	if (!cred.cr_group_info) {
+		put_task_security(sec);
 		return -ENOMEM;
-	ret = set_groups(act_as, cred.cr_group_info);
+	}
+	ret = set_groups(sec, cred.cr_group_info);
 	put_group_info(cred.cr_group_info);
 	if ((cred.cr_uid)) {
-		act_as->cap_effective =
-			cap_drop_nfsd_set(act_as->cap_effective);
+		sec->cap_effective =
+			cap_drop_nfsd_set(sec->cap_effective);
 	} else {
-		act_as->cap_effective =
-			cap_raise_nfsd_set(act_as->cap_effective,
-					   act_as->cap_permitted);
+		sec->cap_effective =
+			cap_raise_nfsd_set(sec->cap_effective,
+					   sec->cap_permitted);
 	}
+
+	/* set the new security as nfsd's subjective security */
+	old = current->act_as;
+	current->act_as = sec;
+	put_task_security(old);
 	return ret;
 }
 
fs/nfsd/nfs4recover.c +40 -24

161 lines not on this page · raw message

author maintainer
#17 lore raw

PATCH 11/37 FS-Cache: Release page->private after failed readahead

In reply to David Howells

The attached patch causes read_cache_pages() to release page-private data on a page for which add_to_page_cache() fails or the filler function fails. This permits pages with caching references associated with them to be cleaned up.

The invalidatepage() address space op is called (indirectly) to do the honours.

---

 mm/readahead.c |   39 +++++++++++++++++++++++++++++++++++++--
 1 files changed, 37 insertions(+), 2 deletions(-)
mm/readahead.c +37 -2
index c9c50ca..75aa6b6 100644
@@ -44,6 +44,41 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 #define list_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private before calling,
+ *   such as the NFS fs marking pages that are cached locally on disk, thus we
+ *   need to give the fs a chance to clean up in the event of an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+					     struct page *page)
+{
+	if (PagePrivate(page)) {
+		if (TestSetPageLocked(page))
+			BUG();
+		page->mapping = mapping;
+		do_invalidatepage(page, 0);
+		page->mapping = NULL;
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+					      struct list_head *pages)
+{
+	struct page *victim;
+
+	while (!list_empty(pages)) {
+		victim = list_to_page(pages);
+		list_del(&victim->lru);
+		read_cache_pages_invalidate_page(mapping, victim);
+	}
+}
+
 /**
  * read_cache_pages - populate an address space with some pages & start reads against them
  * @mapping: the address_space
@@ -65,14 +100,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
-			page_cache_release(page);
+			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
 		page_cache_release(page);
 
 		ret = filler(data, page);
 		if (unlikely(ret)) {
-			put_pages_list(pages);
+			read_cache_pages_invalidate_pages(mapping, pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
author maintainer
#18 lore raw

PATCH 12/37 FS-Cache: Recruit a couple of page flags for cache management

In reply to David Howells

Recruit a couple of page flags to aid in cache management. The following extra flags are defined:

(1) PG_fscache (PG_private_2)

The marked page is backed by a local cache and is pinning resources in the cache driver.

(2) PG_fscache_write (PG_owner_priv_2)

The marked page is being written to the local cache. The page may not be modified whilst this is in progress.

If PG_fscache is set, then things that checked for PG_private will now also check for that. This includes things like truncation and page invalidation. The function page_has_private() had been added to make the checks for both PG_private and PG_private_2 at the same time.

---

 fs/splice.c                |    2 +-
 include/linux/page-flags.h |   39 +++++++++++++++++++++++++++++++++++++--
 include/linux/pagemap.h    |   11 +++++++++++
 mm/filemap.c               |   18 ++++++++++++++++++
 mm/migrate.c               |    2 +-
 mm/page_alloc.c            |    3 +++
 mm/readahead.c             |    9 +++++----
 mm/swap.c                  |    4 ++--
 mm/swap_state.c            |    4 ++--
 mm/truncate.c              |   10 +++++-----
 mm/vmscan.c                |    2 +-
 11 files changed, 86 insertions(+), 18 deletions(-)
fs/splice.c +1 -1
index 4ee49e8..01b8c43 100644
@@ -58,7 +58,7 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
 		 */
 		wait_on_page_writeback(page);
 
-		if (PagePrivate(page))
+		if (page_has_private(page))
 			try_to_release_page(page, GFP_KERNEL);
 
 		/*
include/linux/page-flags.h +37 -2
index bbad43f..cc16c23 100644
@@ -77,25 +77,32 @@
 #define PG_active		 6
 #define PG_slab			 7	/* slab debug (Suparna wants this) */
 
-#define PG_owner_priv_1		 8	/* Owner use. If pagecache, fs may use*/
+#define PG_owner_priv_1		 8	/* Owner use. fs may use in pagecache */
 #define PG_arch_1		 9
 #define PG_reserved		10
 #define PG_private		11	/* If pagecache, has fs-private data */
 
 #define PG_writeback		12	/* Page is under writeback */
+#define PG_private_2		13	/* If pagecache, has fs aux data */
 #define PG_compound		14	/* Part of a compound page */
 #define PG_swapcache		15	/* Swap page: swp_entry_t in private */
 
 #define PG_mappedtodisk		16	/* Has blocks allocated on-disk */
 #define PG_reclaim		17	/* To be reclaimed asap */
+#define PG_owner_priv_2		18	/* Owner use. fs may use in pagecache */
 #define PG_buddy		19	/* Page is free, on buddy lists */
 
 /* PG_readahead is only used for file reads; PG_reclaim is only for writes */
 #define PG_readahead		PG_reclaim /* Reminder to do async read-ahead */
 
-/* PG_owner_priv_1 users should have descriptive aliases */
+/* PG_owner_priv_1/2 users should have descriptive aliases */
 #define PG_checked		PG_owner_priv_1 /* Used by some filesystems */
 #define PG_pinned		PG_owner_priv_1	/* Xen pinned pagetable */
+#define PG_fscache_write	PG_owner_priv_2	/* Writing to local cache */
+
+/* PG_private_2 causes releasepage() and co to be invoked */
+#define PG_fscache		PG_private_2	/* Backed by local cache */
+
 
 #if (BITS_PER_LONG > 32)
 /*
@@ -235,6 +242,23 @@ static inline void SetPageUptodate(struct page *page)
 #define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback,	\
 							&(page)->flags)
 
+#define PagePrivate2(page)	test_bit(PG_private_2, &(page)->flags)
+#define SetPagePrivate2(page)	set_bit(PG_private_2, &(page)->flags)
+#define ClearPagePrivate2(page)	clear_bit(PG_private_2, &(page)->flags)
+#define TestSetPagePrivate2(page) test_and_set_bit(PG_private_2, &(page)->flags)
+#define TestClearPagePrivate2(page) test_and_clear_bit(PG_private_2, \
+						      &(page)->flags)
+
+#define PageOwnerPriv2(page)		test_bit(PG_owner_priv_2, \
+						 &(page)->flags)
+#define SetPageOwnerPriv2(page)		set_bit(PG_owner_priv_2, &(page)->flags)
+#define ClearPageOwnerPriv2(page)	clear_bit(PG_owner_priv_2, \
+						  &(page)->flags)
+#define TestSetPageOwnerPriv2(page)	test_and_set_bit(PG_owner_priv_2, \
+							 &(page)->flags)
+#define TestClearPageOwnerPriv2(page)	test_and_clear_bit(PG_owner_priv_2, \
+							   &(page)->flags)
+
 #define PageBuddy(page)		test_bit(PG_buddy, &(page)->flags)
 #define __SetPageBuddy(page)	__set_bit(PG_buddy, &(page)->flags)
 #define __ClearPageBuddy(page)	__clear_bit(PG_buddy, &(page)->flags)
@@ -308,4 +332,15 @@ static inline void set_page_writeback(struct page *page)
 	test_set_page_writeback(page);
 }
 
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page)			\
+	((page)->flags & ((1 << PG_private) |	\
+			  (1 << PG_private_2)))
+
 #endif	/* PAGE_FLAGS_H */
include/linux/pagemap.h +11 -0
index 4b62a10..51c39f8 100644
@@ -226,6 +226,17 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 
 /*
+ * Wait for a PG_owner_priv_2 to become clear
+ */
+static inline void wait_on_page_owner_priv_2(struct page *page)
+{
+	if (PageOwnerPriv2(page))
+		wait_on_page_bit(page, PG_owner_priv_2);
+}
+
+extern void end_page_owner_priv_2(struct page *page);
+
+/*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *
  * This assumes that two userspace pages are always sufficient.  That's
mm/filemap.c +18 -0
index 5357fcc..138e791 100644
@@ -587,6 +587,21 @@ void end_page_writeback(struct page *page)
 EXPORT_SYMBOL(end_page_writeback);
 
 /**
+ * end_page_own - Clear PG_owner_priv_2 and wake up any waiters
+ * @page: the page
+ *
+ * Clear PG_owner_priv_2 and wake up any processes waiting for that event.
+ */
+void end_page_owner_priv_2(struct page *page)
+{
+	if (!TestClearPageOwnerPriv2(page))
+		BUG();
+	smp_mb__after_clear_bit();
+	wake_up_page(page, PG_owner_priv_2);
+}
+EXPORT_SYMBOL(end_page_owner_priv_2);
+
+/**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
  *
@@ -2570,6 +2585,9 @@ out:
  * (presumably at page->private).  If the release was successful, return `1'.
  * Otherwise return zero.
  *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
  *
mm/migrate.c +1 -1
index 75ae1fb..ba4a9b2 100644
@@ -546,7 +546,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (PagePrivate(page) &&
+	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
mm/page_alloc.c +3 -0
index 26a54a1..e039087 100644
@@ -231,6 +231,7 @@ static void bad_page(struct page *page)
 	dump_stack();
 	page->flags &= ~(1 << PG_lru	|
 			1 << PG_private |
+			1 << PG_fscache	|
 			1 << PG_locked	|
 			1 << PG_active	|
 			1 << PG_dirty	|
@@ -457,6 +458,7 @@ static inline int free_pages_check(struct page *page)
 		(page->flags & (
 			1 << PG_lru	|
 			1 << PG_private |
+			1 << PG_fscache	|
 			1 << PG_locked	|
 			1 << PG_active	|
 			1 << PG_slab	|
@@ -606,6 +608,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 		(page->flags & (
 			1 << PG_lru	|
 			1 << PG_private	|
+			1 << PG_fscache	|
 			1 << PG_locked	|
 			1 << PG_active	|
 			1 << PG_dirty	|
mm/readahead.c +5 -4
index 75aa6b6..272ffc7 100644
@@ -46,14 +46,15 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 /*
  * see if a page needs releasing upon read_cache_pages() failure
- * - the caller of read_cache_pages() may have set PG_private before calling,
- *   such as the NFS fs marking pages that are cached locally on disk, thus we
- *   need to give the fs a chance to clean up in the event of an error
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
  */
 static void read_cache_pages_invalidate_page(struct address_space *mapping,
 					     struct page *page)
 {
-	if (PagePrivate(page)) {
+	if (page_has_private(page)) {
 		if (TestSetPageLocked(page))
 			BUG();
 		page->mapping = mapping;
mm/swap.c +2 -2
index 710a20b..36aa619 100644
@@ -457,8 +457,8 @@ void pagevec_strip(struct pagevec *pvec)
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 
-		if (PagePrivate(page) && !TestSetPageLocked(page)) {
-			if (PagePrivate(page))
+		if (page_has_private(page) && !TestSetPageLocked(page)) {
+			if (page_has_private(page))
 				try_to_release_page(page, 0);
 			unlock_page(page);
 		}
mm/swap_state.c +2 -2
index ec42f01..c3509f2 100644
@@ -73,7 +73,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageSwapCache(page));
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 	error = radix_tree_preload(gfp_mask);
 	if (!error) {
 		write_lock_irq(&swapper_space.tree_lock);
@@ -102,7 +102,7 @@ void __delete_from_swap_cache(struct page *page)
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!PageSwapCache(page));
 	BUG_ON(PageWriteback(page));
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 
 	radix_tree_delete(&swapper_space.page_tree, page_private(page));
 	set_page_private(page, 0);
mm/truncate.c +5 -5
index c35c49e..78b22a1 100644
@@ -49,7 +49,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
 	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, partial);
 }
 
@@ -98,7 +98,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return;
 
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, 0);
 
 	cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -125,7 +125,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, 0))
+	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
 	ret = remove_mapping(mapping, page);
@@ -347,14 +347,14 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
 	write_lock_irq(&mapping->tree_lock);
 	if (PageDirty(page))
 		goto failed;
 
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 	__remove_from_page_cache(page);
 	write_unlock_irq(&mapping->tree_lock);
 	ClearPageUptodate(page);
mm/vmscan.c +1 -1
index a26dabd..e1cc660 100644
@@ -607,7 +607,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * process address space (page_count == 1) it can be freed.
 		 * Otherwise, leave the page on the LRU so it is swappable.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
 			if (!mapping && page_count(page) == 1)
author maintainer
#19 lore raw

PATCH 13/37 FS-Cache: Provide an add_wait_queue_tail() function

In reply to David Howells

Provide an add_wait_queue_tail() function to add a waiter to the back of a wait queue instead of the front.

---

 include/linux/pagemap.h |    7 +++++--
 include/linux/wait.h    |    2 ++
 kernel/wait.c           |   18 ++++++++++++++++++
 mm/filemap.c            |    2 +-
 4 files changed, 26 insertions(+), 3 deletions(-)
include/linux/pagemap.h +5 -2
index 51c39f8..cecbace 100644
@@ -225,8 +225,11 @@ static inline void wait_on_page_writeback(struct page *page)
 
 extern void end_page_writeback(struct page *page);
 
-/*
- * Wait for a PG_owner_priv_2 to become clear
+/**
+ * wait_on_page_owner_priv_2 - Wait for PG_owner_priv_2 to become clear
+ * @page: The page to monitor
+ *
+ * Wait for a PG_owner_priv_2 to become clear on the specified page.
  */
 static inline void wait_on_page_owner_priv_2(struct page *page)
 {
include/linux/wait.h +2 -0
index 33a2aa9..5032ebb 100644
@@ -118,6 +118,8 @@ static inline int waitqueue_active(wait_queue_head_t *q)
 #define is_sync_wait(wait)	(!(wait) || ((wait)->private))
 
 extern void FASTCALL(add_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
+extern void FASTCALL(add_wait_queue_tail(wait_queue_head_t *q,
+					 wait_queue_t *wait));
 extern void FASTCALL(add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t * wait));
 extern void FASTCALL(remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
 
kernel/wait.c +18 -0
index f987688..a82b012 100644
@@ -29,6 +29,24 @@ void fastcall add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(add_wait_queue);
 
+/**
+ * add_wait_queue_tail - Add a waiter to the back of a waitqueue
+ * @q: the wait queue to append the waiter to
+ * @wait: the waiter to be queued
+ *
+ * Add a waiter to the back of a waitqueue so that it gets woken up last.
+ */
+void fastcall add_wait_queue_tail(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue_tail(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(add_wait_queue_tail);
+
 void fastcall add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	unsigned long flags;
mm/filemap.c +1 -1
index 138e791..8d64000 100644
@@ -587,7 +587,7 @@ void end_page_writeback(struct page *page)
 EXPORT_SYMBOL(end_page_writeback);
 
 /**
- * end_page_own - Clear PG_owner_priv_2 and wake up any waiters
+ * end_page_owner_priv_2 - Clear PG_owner_priv_2 and wake up any waiters
  * @page: the page
  *
  * Clear PG_owner_priv_2 and wake up any processes waiting for that event.
author maintainer
#20 lore raw

PATCH 14/37 FS-Cache: Generic filesystem caching facility

In reply to David Howells

The attached patch adds a generic intermediary (FS-Cache) by which filesystems may call on local caching capabilities, and by which local caching backends may make caches available:

	+---------+
	|         |                        +--------------+
	|   NFS   |--+                     |              |
	|         |  |                 +-->|   CacheFS    |
	+---------+  |   +----------+  |   |  /dev/hda5   |
	             |   |          |  |   +--------------+
	+---------+  +-->|          |  |
	|         |      |          |--+
	|   AFS   |----->| FS-Cache |
	|         |      |          |--+
	+---------+  +-->|          |  |
	             |   |          |  |   +--------------+
	+---------+  |   +----------+  |   |              |
	|         |  |                 +-->|  CacheFiles  |
	|  ISOFS  |--+                     |  /var/cache  |
	|         |                        +--------------+
	+---------+

The patch also documents the netfs interface and the cache backend interface provided by the facility.

There are a number of reasons why I'm not using i_mapping to do this. These have been discussed a lot on the LKML and CacheFS mailing lists, but to summarise the basics:

(1) Most filesystems don't do hole reportage. Holes in files are treated as blocks of zeros and can't be distinguished otherwise, making it difficult to distinguish blocks that have been read from the network and cached from those that haven't.

(2) The backing inode must be fully populated before being exposed to userspace through the main inode because the VM/VFS goes directly to the backing inode and does not interrogate the front inode on VM ops.

Therefore:

(a) The backing inode must fit entirely within the cache.

(b) All backed files currently open must fit entirely within the cache at the same time.

(c) A working set of files in total larger than the cache may not be cached.

(d) A file may not grow larger than the available space in the cache.

(e) A file that's open and cached, and remotely grows larger than the cache is potentially stuffed.

(3) Writes go to the backing filesystem, and can only be transferred to the network when the file is closed.

(4) There's no record of what changes have been made, so the whole file must be written back.

(5) The pages belong to the backing filesystem, and all metadata associated with that page are relevant only to the backing filesystem, and not anything stacked atop it.

The attached patch adds a generic core to which both networking filesystems and caches may bind. It transfers requests from networking filesystems to appropriate caches if possible, or else gracefully denies them.

If this facility is disabled in the kernel configuration, then all its operations will be trivially reducible to nothing by the compiler.

FS-Cache provides the following facilities:

(1) Caches can be added / removed at any time, even whilst in use.

(2) Adds a facility by which tags can be used to refer to caches, even if they're not mounted yet.

(3) More than one cache can be used at once. Caches can be selected explicitly by use of tags.

(4) The netfs is provided with an interface that allows either party to withdraw caching facilities from a file (required for (1)).

(5) A netfs may annotate cache objects that belongs to it.

(6) Cache objects can be pinned and reservations made.

(7) The interface to the netfs returns as few errors as possible, preferring rather to let the netfs remain oblivious.

(8) Cookies are used to represent indices, files and other objects to the netfs. The simplest cookie is just a NULL pointer - indicating nothing cached there.

(9) The netfs is allowed to propose - dynamically - any index hierarchy it desires, though it must be aware that the index search function is recursive, stack space is limited, and indices can only be children of indices.

(10) Indices can be used to group files together to reduce key size and to make group invalidation easier. The use of indices may make lookup quicker, but that's cache dependent.

(11) Data I/O is effectively done directly to and from the netfs's pages. The netfs indicates that page A is at index B of the data-file represented by cookie C, and that it should be read or written. The cache backend may or may not start I/O on that page, but if it does, a netfs callback will be invoked to indicate completion. The I/O may be either synchronous or asynchronous.

(12) Cookies can be "retired" upon release. At this point FS-Cache will mark them as obsolete and the index hierarchy rooted at that point will get recycled.

(13) The netfs provides a "match" function for index searches. In addition to saying whether a match was made or not, this can also specify that an entry should be updated or deleted.

FS-Cache maintains a virtual indexing tree in which all indices, files, objects and pages are kept. Bits of this tree may actually reside in one or more caches.

FSDEF
|
+------------------------------------+
| |
NFS AFS
| |
+--------------------------+ +-----------+
| | | |
homedir mirror afs.org redhat.com
| | |
+------------+ +---------------+ +----------+
| | | | | |
00001 00002 00007 00125 vol00001 vol00002

     |            |           |               |                         |
 +---+---+     +-----+      +---+      +------+------+            +-----+----+
 |   |   |     |     |      |   |      |      |      |            |     |    |
PG0 PG1 PG2   PG0  XATTR   PG0 PG1   DIRENT DIRENT DIRENT        R/W   R/O  Bak
                     |                                            |
                    PG0                                       +-------+
                                                              |       |
                                                            00001   00003
                                                              |
                                                          +---+---+
                                                          |   |   |
                                                         PG0 PG1 PG2

In the example above, you can see two netfs's being backed: NFS and AFS. These have different index hierarchies:

(*) The NFS primary index will probably contain per-server indices. Each
server index is indexed by NFS file handles to get data file objects. Each data file objects can have an array of pages, but may also have further child objects, such as extended attributes and directory entries. Extended attribute objects themselves have page-array contents.

(*) The AFS primary index contains per-cell indices. Each cell index contains
per-logical-volume indices. Each of volume index contains up to three indices for the read-write, read-only and backup mirrors of those volumes. Each of these contains vnode data file objects, each of which contains an array of pages.

The very top index is the FS-Cache master index in which individual netfs's have entries.

Any index object may reside in more than one cache, provided it only has index children. Any index with non-index object children will be assumed to only reside in one cache.

The FS-Cache overview can be found in:

Documentation/filesystems/caching/fscache.txt

The netfs API to FS-Cache can be found in:

Documentation/filesystems/caching/netfs-api.txt

The cache backend API to FS-Cache can be found in:

Documentation/filesystems/caching/backend-api.txt

---

 Documentation/filesystems/caching/backend-api.txt |  625 +++++++++++++++
 Documentation/filesystems/caching/fscache.txt     |  295 +++++++
 Documentation/filesystems/caching/netfs-api.txt   |  741 ++++++++++++++++++
 fs/Kconfig                                        |    6 
 fs/Makefile                                       |    1 
 fs/fscache/Kconfig                                |   49 +
 fs/fscache/Makefile                               |   19 
 fs/fscache/fsc-cache.c                            |  493 ++++++++++++
 fs/fscache/fsc-cookie.c                           |  490 ++++++++++++
 fs/fscache/fsc-fsdef.c                            |  112 +++
 fs/fscache/fsc-internal.h                         |  376 +++++++++
 fs/fscache/fsc-main.c                             |  122 +++
 fs/fscache/fsc-manage.c                           |  257 ++++++
 fs/fscache/fsc-object.c                           |  583 ++++++++++++++
 fs/fscache/fsc-page.c                             |  872 +++++++++++++++++++++
 fs/fscache/fsc-proc.c                             |  404 ++++++++++
 fs/fscache/fsc-stats.c                            |  103 ++
 fs/fscache/fsc-threads.c                          |  676 ++++++++++++++++
 include/linux/fscache-cache.h                     |  433 ++++++++++
 include/linux/fscache.h                           |  617 +++++++++++++++
 include/linux/pagemap.h                           |    4 
 mm/filemap.c                                      |    2 
 22 files changed, 7279 insertions(+), 1 deletions(-)
 create mode 100644 Documentation/filesystems/caching/backend-api.txt
 create mode 100644 Documentation/filesystems/caching/fscache.txt
 create mode 100644 Documentation/filesystems/caching/netfs-api.txt
 create mode 100644 fs/fscache/Kconfig
 create mode 100644 fs/fscache/Makefile
 create mode 100644 fs/fscache/fsc-cache.c
 create mode 100644 fs/fscache/fsc-cookie.c
 create mode 100644 fs/fscache/fsc-fsdef.c
 create mode 100644 fs/fscache/fsc-internal.h
 create mode 100644 fs/fscache/fsc-main.c
 create mode 100644 fs/fscache/fsc-manage.c
 create mode 100644 fs/fscache/fsc-object.c
 create mode 100644 fs/fscache/fsc-page.c
 create mode 100644 fs/fscache/fsc-proc.c
 create mode 100644 fs/fscache/fsc-stats.c
 create mode 100644 fs/fscache/fsc-threads.c
 create mode 100644 include/linux/fscache-cache.h
 create mode 100644 include/linux/fscache.h
Documentation/filesystems/caching/backend-api.txt new file +625 -0
new file mode 100644
index 0000000..a7e58eb
@@ -0,0 +1,625 @@
+			  ==========================
+			  FS-CACHE CACHE BACKEND API
+			  ==========================
+
+The FS-Cache system provides an API by which actual caches can be supplied to
+FS-Cache for it to then serve out to network filesystems and other interested
+parties.
+
+This API is declared in <linux/fscache-cache.h>.
+
+
+====================================
+INITIALISING AND REGISTERING A CACHE
+====================================
+
+To start off, a cache definition must be initialised and registered for each
+cache the backend wants to make available.  For instance, CacheFS does this in
+the fill_super() operation on mounting.
+
+The cache definition (struct fscache_cache) should be initialised by calling:
+
+	void fscache_init_cache(struct fscache_cache *cache,
+				struct fscache_cache_ops *ops,
+				const char *idfmt,
+				...);
+
+Where:
+
+ (*) "cache" is a pointer to the cache definition;
+
+ (*) "ops" is a pointer to the table of operations that the backend supports on
+     this cache; and
+
+ (*) "idfmt" is a format and printf-style arguments for constructing a label
+     for the cache.
+
+
+The cache should then be registered with FS-Cache by passing a pointer to the
+previously initialised cache definition to:
+
+	int fscache_add_cache(struct fscache_cache *cache,
+			      struct fscache_object *fsdef,
+			      const char *tagname);
+
+Two extra arguments should also be supplied:
+
+ (*) "fsdef" which should point to the object representation for the FS-Cache
+     master index in this cache.  Netfs primary index entries will be created
+     here.
+
+ (*) "tagname" which, if given, should be a text string naming this cache.  If
+     this is NULL, the identifier will be used instead.  For CacheFS, the
+     identifier is set to name the underlying block device and the tag can be
+     supplied by mount.
+
+This function may return -ENOMEM if it ran out of memory or -EEXIST if the tag
+is already in use.  0 will be returned on success.
+
+
+=====================
+UNREGISTERING A CACHE
+=====================
+
+A cache can be withdrawn from the system by calling this function with a
+pointer to the cache definition:
+
+	void fscache_withdraw_cache(struct fscache_cache *cache);
+
+In CacheFS's case, this is called by put_super().
+
+
+========
+SECURITY
+========
+
+The cache methods are executed one of two contexts:
+
+ (1) that of the userspace process that issued the netfs operation that caused
+     the cache method to be invoked, or
+
+ (2) that of one of the processes in the FS-Cache thread pool.
+
+In either case, this may not be an appropriate context in which to access the
+cache.
+
+The calling process's fsuid, fsgid and SELinux security identities may need to
+be masqueraded for the duration of the cache driver's access to the cache.
+This is left to the cache to handle; FS-Cache makes no effort in this regard.
+
+
+===================================
+CONTROL AND STATISTICS PRESENTATION
+===================================
+
+The cache may present data to the outside world through FS-Cache's interfaces
+in sysfs and procfs - the former for control and the latter for statistics.
+
+A sysfs directory called /sys/fs/fscache/<cachetag>/ is created if CONFIG_SYSFS
+is enabled.  This is accessible through the kobject struct fscache_cache::kobj
+and is for use by the cache as it sees fit.
+
+The cache driver may create itself a directory named for the cache type in the
+/proc/fs/fscache/ directory.  This is available if CONFIG_FSCACHE_PROC is
+enabled and is accessible through:
+
+	struct proc_dir_entry *proc_fscache;
+
+
+========================
+RELEVANT DATA STRUCTURES
+========================
+
+ (*) Index/Data file FS-Cache representation cookie:
+
+	struct fscache_cookie {
+		struct fscache_object_def	*def;
+		struct fscache_netfs		*netfs;
+		void				*netfs_data;
+		...
+	};
+
+     The fields that might be of use to the backend describe the object
+     definition, the netfs definition and the netfs's data for this cookie.
+     The object definition contain functions supplied by the netfs for loading
+     and matching index entries; these are required to provide some of the
+     cache operations.
+
+
+ (*) In-cache object representation:
+
+	struct fscache_object {
+		int				debug_id;
+		enum {
+			FSCACHE_OBJECT_RECYCLING,
+			...
+		}				state;
+		spinlock_t			lock
+		struct fscache_cache		*cache;
+		struct fscache_cookie		*cookie;
+		...
+	};
+
+     Structures of this type should be allocated by the cache backend and
+     passed to FS-Cache when requested by the appropriate cache operation.  In
+     the case of CacheFS, they're embedded in CacheFS's internal object
+     structures.
+
+     The debug_id is a simple integer that can be used in debugging messages
+     that refer to a particular object.  In such a case it should be printed
+     using "OBJ%x" to be consistent with FS-Cache.
+
+     Each object contains a pointer to the cookie that represents the object it
+     is backing.  An object should retired when put_object() is called if it is
+     in state FSCACHE_OBJECT_RECYCLING.  The fscache_object struct should be
+     initialised by calling fscache_object_init(object).
+
+
+ (*) FS-Cache operation record:
+
+	struct fscache_operation {
+		atomic_t		usage;
+		struct fscache_object	*object;
+		unsigned long		flags;
+	#define FSCACHE_OP_EXCLUSIVE
+		void (*processor)(struct fscache_operation *op);
+		void (*release)(struct fscache_operation *op);
+		...
+	};
+
+     FS-Cache has a pool of threads that it uses to give CPU time to the
+     various asynchronous operations that need to be done as part of driving
+     the cache.  These are represented by the above structure.  The processor
+     method is called to give the op CPU time, and the release method to get
+     rid of it when its usage count reaches 0.
+
+     An operation can be made exclusive upon an object by setting the
+     appropriate flag before enqueuing it with fscache_enqueue_operation().  If
+     an operation needs more processing time, it should be enqueued again.
+
+
+ (*) FS-Cache retrieval operation record:
+
+	struct fscache_retrieval {
+		struct fscache_operation op;
+		struct address_space	*mapping;
+		struct list_head	*to_do;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record retrieval and
+     allocation requests made by the netfs.  This struct is then passed to the
+     backend to do the operation.  The backend may get extra refs to it by
+     calling fscache_get_retrieval() and refs may be discarded by calling
+     fscache_put_retrieval().
+
+     A retrieval operation can be used by the backend to do retrieval work.  To
+     do this, the retrieval->op.processor method pointer should be set
+     appropriately by the backend and fscache_enqueue_retrieval() called to
+     submit it to the thread pool.  CacheFiles, for example, uses this to queue
+     page examination when it detects PG_lock being cleared.
+
+     The to_do field is an empty list available for the cache backend to use as
+     it sees fit.
+
+
+ (*) FS-Cache storage operation record:
+
+	struct fscache_storage {
+		struct fscache_operation op;
+		pgoff_t			store_limit;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record outstanding
+     writes to be made.  FS-Cache itself enqueues this operation and invokes
+     the write_page() method on the object at appropriate times to effect
+     storage.
+
+
+================
+CACHE OPERATIONS
+================
+
+The cache backend provides FS-Cache with a table of operations that can be
+performed on the denizens of the cache.  These are held in a structure of type:
+
+	struct fscache_cache_ops
+
+ (*) Name of cache provider [mandatory]:
+
+	const char *name
+
+     This isn't strictly an operation, but should be pointed at a string naming
+     the backend.
+
+
+ (*) Allocate a new object [mandatory]:
+
+	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+					       struct fscache_cookie *cookie)
+
+     This method is used to allocate a cache object representation to back a
+     cookie in a particular cache.  fscache_object_init() should be called on
+     the object to initialise it prior to returning.
+
+     This function may also be used to parse the index key to be used for
+     multiple lookup calls to turn it into a more convenient form.  FS-Cache
+     will call the lookup_complete() method to allow the cache to release the
+     form once lookup is complete or aborted.
+
+
+ (*) Look up and create object [mandatory]:
+
+	void (*lookup_object)(struct fscache_object *object)
+
+     This method is used to look up an object, given that the object is already
+     allocated and attached to the cookie.  This should instantiate that object
+     in the cache if it can.
+
+     The method should call fscache_object_lookup_negative() as soon as
+     possible if it determines the object doesn't exist in the cache.  If the
+     object is found to exist and the netfs indicates that it is valid then
+     fscache_obtained_object() should be called once the object is in a
+     position to have data stored in it.  Similarly, fscache_obtained_object()
+     should also be called once a non-present object has been created.
+
+     If a lookup error occurs, fscache_object_lookup_error() should be called
+     to abort the lookup of that object.
+
+
+ (*) Release lookup data [mandatory]:
+
+	void (*lookup_complete)(struct fscache_object *object)
+
+     This method is called to ask the cache to release any resources it was
+     using to perform a lookup.
+
+
+ (*) Increment object refcount [mandatory]:
+
+	struct fscache_object *(*grab_object)(struct fscache_object *object)
+
+     This method is called to increment the reference count on an object.  It
+     may fail (for instance if the cache is being withdrawn) by returning NULL.
+     It should return the object pointer if successful.
+
+
+ (*) Lock/Unlock object [mandatory]:
+
+	void (*lock_object)(struct fscache_object *object)
+	void (*unlock_object)(struct fscache_object *object)
+
+     These methods are used to exclusively lock an object.  It must be possible
+     to schedule with the lock held, so a spinlock isn't sufficient.
+
+
+ (*) Pin/Unpin object [optional]:
+
+	int (*pin_object)(struct fscache_object *object)
+	void (*unpin_object)(struct fscache_object *object)
+
+     These methods are used to pin an object into the cache.  Once pinned an
+     object cannot be reclaimed to make space.  Return -ENOSPC if there's not
+     enough space in the cache to permit this.
+
+
+ (*) Update object [mandatory]:
+
+	int (*update_object)(struct fscache_object *object)
+
+     This is called to update the index entry for the specified object.  The
+     new information should be in object->cookie->netfs_data.  This can be
+     obtained by calling object->cookie->def->get_aux()/get_attr().
+
+
+ (*) Discard object [mandatory]:
+
+	void (*drop_object)(struct fscache_object *object)
+
+     This method is called to indicate that an object has been unbound from its
+     cookie, and that the cache should release the object's resources and
+     retire it if it's in state FSCACHE_OBJECT_RECYCLING.
+
+     This method should not attempt to release any references held by the
+     caller.  The caller will invoke the put_object() method as appropriate.
+
+
+ (*) Release object reference [mandatory]:
+
+	void (*put_object)(struct fscache_object *object)
+
+     This method is used to discard a reference to an object.  The object may
+     be freed when all the references to it are released.
+
+
+ (*) Synchronise a cache [mandatory]:
+
+	void (*sync)(struct fscache_cache *cache)
+
+     This is called to ask the backend to synchronise a cache with its backing
+     device.
+
+
+ (*) Dissociate a cache [mandatory]:
+
+	void (*dissociate_pages)(struct fscache_cache *cache)
+
+     This is called to ask a cache to perform any page dissociations as part of
+     cache withdrawal.
+
+
+ (*) Notification that the attributes on a netfs file changed [mandatory]:
+
+	int (*attr_changed)(struct fscache_object *object);
+
+     This is called to indicate to the cache that certain attributes on a netfs
+     file have changed (for example the maximum size a file may reach).  The
+     cache can read these from the netfs by calling the cookie's get_attr()
+     method.
+
+     The cache may use the file size information to reserve space on the cache.
+     It should also call fscache_set_store_limit() to indicate to FS-Cache the
+     highest byte it's willing to store for an object.
+
+     This method may return -ve if an error occurred or the cache object cannot
+     be expanded.  In such a case, the object will be withdrawn from service.
+
+     This operation is run asynchronously from FS-Cache's thread pool, and
+     storage and retrieval operations from the netfs are excluded during the
+     execution of this operation.
+
+
+ (*) Reserve cache space for an object's data [optional]:
+
+	int (*reserve_space)(struct fscache_object *object, loff_t size);
+
+     This is called to request that cache space be reserved to hold the data
+     for an object and the metadata used to track it.  Zero size should be
+     taken as request to cancel a reservation.
+
+     This should return 0 if successful, -ENOSPC if there isn't enough space
+     available, or -ENOMEM or -EIO on other errors.
+
+     The reservation may exceed the current size of the object, thus permitting
+     future expansion.  If the amount of space consumed by an object would
+     exceed the reservation, it's permitted to refuse requests to allocate
+     pages, but not required.  An object may be pruned down to its reservation
+     size if larger than that already.
+
+
+ (*) Request page be read from cache [mandatory]:
+
+	int (*read_or_alloc_page)(struct fscache_retrieval *op,
+				  struct page *page,
+				  gfp_t gfp)
+
+     This is called to attempt to read a netfs page from the cache, or to
+     reserve a backing block if not.  FS-Cache will have done as much checking
+     as it can before calling, but most of the work belongs to the backend.
+
+     If there's no page in the cache, then -ENODATA should be returned if the
+     backend managed to reserve a backing block; -ENOBUFS or -ENOMEM if it
+     didn't.
+
+     If there is suitable data in the cache, then a read operation should be
+     queued and 0 returned.  When the read finishes, fscache_end_io() should be
+     called.
+
+     The fscache_mark_pages_cached() should be called for the page if any cache
+     metadata is retained.  This will indicate to the netfs that the page needs
+     explicit uncaching.  This operation takes a pagevec, thus allowing several
+     pages to be marked at once.
+
+     The retrieval record pointed to by op should be retained for each page
+     queued and released when I/O on the page has been formally ended.
+     fscache_get/put_retrieval() are available for this purpose.
+
+     The retrieval record may be used to get CPU time via the FS-Cache thread
+     pool.  If this is desired, the op->op.processor should be set to point to
+     the appropriate processing routine, and fscache_enqueue_retrieval() should
+     be called at an appropriate point to request CPU time.  For instance, the
+     retrieval routine could be enqueued upon the completion of a disk read.
+     The to_do field in the retrieval record is provided to aid in this.
+
+     If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS
+     returned if possible or fscache_end_io() called with a suitable error
+     code..
+
+
+ (*) Request pages be read from cache [mandatory]:
+
+	int (*read_or_alloc_pages)(struct fscache_retrieval *op,
+				   struct list_head *pages,
+				   unsigned *nr_pages,
+				   gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except it is handed a list
+     of pages instead of one page.  Any pages on which a read operation is
+     started must be added to the page cache for the specified mapping and also
+     to the LRU.  Such pages must also be removed from the pages list and
+     *nr_pages decremented per page.
+
+     If there was an error such as -ENOMEM, then that should be returned; else
+     if one or more pages couldn't be read or allocated, then -ENOBUFS should
+     be returned; else if one or more pages couldn't be read, then -ENODATA
+     should be returned.  If all the pages are dispatched then 0 should be
+     returned.
+
+
+ (*) Request page be allocated in the cache [mandatory]:
+
+	int (*allocate_page)(struct fscache_retrieval *op,
+			     struct page *page,
+			     gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except that it shouldn't
+     read from the cache, even if there's data there that could be retrieved.
+     It should, however, set up any internal metadata required such that
+     the write_page() method can write to the cache.
+
+     If there's no backing block available, then -ENOBUFS should be returned
+     (or -ENOMEM if there were other problems).  If a block is successfully
+     allocated, then the netfs page should be marked and 0 returned.
+
+
+ (*) Request pages be allocated in the cache [mandatory]:
+
+	int (*allocate_pages)(struct fscache_retrieval *op,
+			      struct list_head *pages,
+			      unsigned *nr_pages,
+			      gfp_t gfp)
+
+     This is an multiple page version of the allocate_page() method.  pages and
+     nr_pages should be treated as for the read_or_alloc_pages() method.
+
+
+ (*) Request page be written to cache [mandatory]:
+
+	int (*write_page)(struct fscache_storage *op,
+			  struct page *page);
+
+     This is called to write from a page on which there was a previously
+     successful read_or_alloc_page() call or similar.  FS-Cache filters out
+     pages that don't have mappings.
+
+     This method is called asynchronously from the FS-Cache thread pool.  It is
+     not required to actually store anything, provided -ENODATA is then
+     returned to the next read of this page.
+
+     If an error occurred, then a negative error code should be returned,
+     otherwise zero should be returned.  FS-Cache will take appropriate action
+     in response to an error, such as withdrawing this object.
+
+     If this method returns success then FS-Cache will inform the netfs
+     appropriately.
+
+
+ (*) Discard retained per-page metadata [mandatory]:
+
+	void (*uncache_page)(struct fscache_object *object, struct page *page)
+
+     This is called when a netfs page is being evicted from the pagecache.  The
+     cache backend should tear down any internal representation or tracking it
+     maintains for this page.
+
+
+==================
+FS-CACHE UTILITIES
+==================
+
+FS-Cache provides some utilities that a cache backend may make use of:
+
+ (*) Note occurrence of an I/O error in a cache:
+
+	void fscache_io_error(struct fscache_cache *cache)
+
+     This tells FS-Cache that an I/O error occurred in the cache.  After this
+     has been called, only resource dissociation operations (object and page
+     release) will be passed from the netfs to the cache backend for the
+     specified cache.
+
+     This does not actually withdraw the cache.  That must be done separately.
+
+
+ (*) Invoke the retrieval I/O completion function:
+
+	void fscache_end_io(struct fscache_retrieval *op, struct page *page,
+			    int error);
+
+     This is called to note the end of an attempt to retrieve a page.  The
+     error value should be 0 if successful and an error otherwise.
+
+
+ (*) Set highest store limit:
+
+	void fscache_set_store_limit(struct fscache_object *object,
+				     loff_t i_size);
+
+     This sets the limit FS-Cache imposes on the highest byte it's willing to
+     try and store for a netfs.  Any page over this limit is automatically
+     rejected by fscache_read_alloc_page() and co with -ENOBUFS.
+
+
+ (*) Mark pages as being cached:
+
+	void fscache_mark_pages_cached(struct fscache_retrieval *op,
+				       struct pagevec *pagevec);
+
+     This marks a set of pages as being cached.  After this has been called,
+     the netfs must call fscache_uncache_page() to unmark the pages.
+
+
+ (*) Initialise a freshly allocated object:
+
+	void fscache_object_init(struct fscache_object *object);
+
+     This initialises all the fields in an object representation.
+
+
+ (*) Indicate negative lookup on an object:
+
+	void fscache_object_lookup_negative(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     found a negative result.
+
+     This changes the state of an object to permit reads pending on lookup
+     completion to go off and start fetching data from the netfs server as it's
+     known at this point that there can't be any data in the cache.
+
+     This may be called multiple times on an object.  Only the first call is
+     significant - all subsequent calls are ignored.
+
+
+ (*) Indicate an object has been obtained:
+
+	void fscache_obtained_object(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     produced a positive result, or that an object was created.  This should
+     only be called once for any particular object.
+
+     This changes the state of an object to indicate:
+
+	(1) if no call to fscache_object_lookup_negative() has been made on
+	    this object, that there may be data available, and that reads can
+	    now go and look for it; and
+
+        (2) that writes may now proceed against this object.
+
+
+ (*) Indicate that object lookup failed:
+
+	void fscache_object_lookup_error(struct fscache_object *object);
+
+     This marks an object as having encountered a fatal error (usually EIO)
+     and causes it to move into a state whereby it will be withdrawn as soon
+     as possible.
+
+
+ (*) Get and release references on a retrieval record:
+
+	void fscache_get_retrieval(struct fscache_retrieval *op);
+	void fscache_put_retrieval(struct fscache_retrieval *op);
+
+     These two functions are used to retain a retrieval record whilst doing
+     asynchronous data retrieval and block allocation.
+
+
+ (*) Enqueue a retrieval record for processing.
+
+	void fscache_enqueue_retrieval(struct fscache_retrieval *op);
+
+     This enqueues a retrieval record for processing by the FS-Cache thread
+     pool.  One of the threads in the pool will invoke the retrieval record's
+     op->op.processor callback function.  This function may be called from
+     within the callback function.
+
+
+ (*) List of object state names:
+
+	const char *fscache_object_states[];
+
+     For debugging purposes, this may be used to turn the state that an object
+     is in into a text string for display purposes.
Documentation/filesystems/caching/fscache.txt new file +295 -0

295 lines not on this page · raw message

Documentation/filesystems/caching/netfs-api.txt new file +741 -0

741 lines not on this page · raw message

fs/Kconfig +6 -0
index d731282..80264c0 100644
@@ -618,6 +618,12 @@ config GENERIC_ACL
 	bool
 	select FS_POSIX_ACL
 
+menu "Caches"
+
+source "fs/fscache/Kconfig"
+
+endmenu
+
 if BLOCK
 menu "CD-ROM/DVD Filesystems"
 
fs/Makefile +1 -0
index 1e7a11b..11e47bf 100644
@@ -66,6 +66,7 @@ obj-$(CONFIG_PROFILING)		+= dcookies.o
 obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
+obj-$(CONFIG_FSCACHE)		+= fscache/
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
 obj-$(CONFIG_EXT4DEV_FS)	+= ext4/ # Before ext2 so root fs can be ext4dev
fs/fscache/Kconfig new file +49 -0

49 lines not on this page · raw message

fs/fscache/Makefile new file +19 -0
new file mode 100644
index 0000000..e60dad3
@@ -0,0 +1,19 @@
+#
+# Makefile for general filesystem caching code
+#
+
+fscache-y := \
+	fsc-cache.o \
+	fsc-cookie.o \
+	fsc-fsdef.o \
+	fsc-main.o \
+	fsc-manage.o \
+	fsc-object.o \
+	fsc-page.o \
+	fsc-threads.o
+
+fscache-$(CONFIG_FSCACHE_PROC) += \
+	fsc-proc.o \
+	fsc-stats.o
+
+obj-$(CONFIG_FSCACHE) := fscache.o
fs/fscache/fsc-cache.c new file +493 -0

493 lines not on this page · raw message

fs/fscache/fsc-cookie.c new file +490 -0

490 lines not on this page · raw message

fs/fscache/fsc-fsdef.c new file +112 -0

112 lines not on this page · raw message

fs/fscache/fsc-internal.h new file +376 -0

157 lines not on this page · raw message

fs/fscache/fsc-main.c new file +122 -0

122 lines not on this page · raw message

fs/fscache/fsc-manage.c new file +257 -0

257 lines not on this page · raw message

fs/fscache/fsc-object.c new file +583 -0

583 lines not on this page · raw message

fs/fscache/fsc-page.c new file +872 -0

872 lines not on this page · raw message

fs/fscache/fsc-proc.c new file +404 -0

404 lines not on this page · raw message

fs/fscache/fsc-stats.c new file +103 -0

103 lines not on this page · raw message

fs/fscache/fsc-threads.c new file +676 -0

676 lines not on this page · raw message

include/linux/fscache-cache.h new file +433 -0

433 lines not on this page · raw message

include/linux/fscache.h new file +617 -0

617 lines not on this page · raw message

include/linux/pagemap.h +3 -1
index cecbace..d22e975 100644

Lines of this file are not shown. View the raw message.

mm/filemap.c +2 -0
index 8d64000..89f5a5e 100644

Lines of this file are not shown. View the raw message.

The rest of this diff is not shown. View the raw message.

Part of the diff is not shown here. View the raw message.

author maintainer
#21 lore raw

PATCH 15/37 CacheFiles: Add missing copy_page export for ia64

In reply to David Howells

This one-line patch fixes the missing export of copy_page introduced by the cachefile patches. This patch is not yet upstream, but is required for cachefile on ia64. It will be pushed upstream when cachefile goes upstream.

---

 arch/ia64/kernel/ia64_ksyms.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)
arch/ia64/kernel/ia64_ksyms.c +1 -0
index 8e7193d..3e544f4 100644
@@ -46,6 +46,7 @@ EXPORT_SYMBOL(__do_clear_user);
 EXPORT_SYMBOL(__strlen_user);
 EXPORT_SYMBOL(__strncpy_from_user);
 EXPORT_SYMBOL(__strnlen_user);
+EXPORT_SYMBOL(copy_page);
 
 /* from arch/ia64/lib */
 extern void __divsi3(void);
author maintainer
#22 lore raw

PATCH 16/37 CacheFiles: Be consistent about the use of mapping vs file->f_mapping in Ext3

In reply to David Howells

Change all the usages of file->f_mapping in ext3_*write_end() functions to use the mapping argument directly. This has two consequences:

(*) Consistency. Without this patch sometimes one is used and sometimes the
other is.

(*) A NULL file pointer can be passed. This feature is then made use of by
the generic hook in the next patch, which is used by CacheFiles to write pages to a file without setting up a file struct.

---

 fs/ext3/inode.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)
fs/ext3/inode.c +3 -3
index eb95670..c976123 100644
@@ -1215,7 +1215,7 @@ static int ext3_generic_write_end(struct file *file,
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata)
 {
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = mapping->host;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
@@ -1240,7 +1240,7 @@ static int ext3_ordered_write_end(struct file *file,
 				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = mapping->host;
 	unsigned from, to;
 	int ret = 0, ret2;
 
@@ -1281,7 +1281,7 @@ static int ext3_writeback_write_end(struct file *file,
 				struct page *page, void *fsdata)
 {
 	handle_t *handle = ext3_journal_current_handle();
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 	loff_t new_i_size;
 
author maintainer
#23 lore raw

PATCH 17/37 CacheFiles: Add a hook to write a single page of data to an inode

In reply to David Howells

Add an address space operation to write one single page of data to an inode at a page-aligned location (thus permitting the implementation to be highly optimised). The data source is a single page.

This is used by CacheFiles to store the contents of netfs pages into their backing file pages.

Supply a generic implementation for this that uses the write_begin() and write_end() address_space operations to bind a copy directly into the page cache.

Hook the Ext2 and Ext3 operations to the generic implementation.

---

 fs/ext2/inode.c    |    2 ++
 fs/ext3/inode.c    |    3 +++
 include/linux/fs.h |    7 ++++++
 mm/filemap.c       |   61 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 73 insertions(+), 0 deletions(-)
fs/ext2/inode.c +2 -0
index c620068..f483014 100644
@@ -792,6 +792,7 @@ const struct address_space_operations ext2_aops = {
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
+	.write_one_page		= generic_file_buffered_write_one_page,
 };
 
 const struct address_space_operations ext2_aops_xip = {
@@ -810,6 +811,7 @@ const struct address_space_operations ext2_nobh_aops = {
 	.direct_IO		= ext2_direct_IO,
 	.writepages		= ext2_writepages,
 	.migratepage		= buffer_migrate_page,
+	.write_one_page		= generic_file_buffered_write_one_page,
 };
 
 /*
fs/ext3/inode.c +3 -0
index c976123..0209f3b 100644
@@ -1776,6 +1776,7 @@ static const struct address_space_operations ext3_ordered_aops = {
 	.releasepage	= ext3_releasepage,
 	.direct_IO	= ext3_direct_IO,
 	.migratepage	= buffer_migrate_page,
+	.write_one_page	= generic_file_buffered_write_one_page,
 };
 
 static const struct address_space_operations ext3_writeback_aops = {
@@ -1790,6 +1791,7 @@ static const struct address_space_operations ext3_writeback_aops = {
 	.releasepage	= ext3_releasepage,
 	.direct_IO	= ext3_direct_IO,
 	.migratepage	= buffer_migrate_page,
+	.write_one_page	= generic_file_buffered_write_one_page,
 };
 
 static const struct address_space_operations ext3_journalled_aops = {
@@ -1803,6 +1805,7 @@ static const struct address_space_operations ext3_journalled_aops = {
 	.bmap		= ext3_bmap,
 	.invalidatepage	= ext3_invalidatepage,
 	.releasepage	= ext3_releasepage,
+	.write_one_page	= generic_file_buffered_write_one_page,
 };
 
 void ext3_set_aops(struct inode *inode)
include/linux/fs.h +7 -0
index feea65d..35525c4 100644
@@ -481,6 +481,11 @@ struct address_space_operations {
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *);
 	int (*launder_page) (struct page *);
+	/* write the contents of the source page over the page at the specified
+	 * index in the target address space (the source page does not need to
+	 * be related to the target address space) */
+	int (*write_one_page)(struct address_space *, pgoff_t, struct page *);
+
 };
 
 /*
@@ -1805,6 +1810,8 @@ extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, loff_t *, size_t, size_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t, loff_t *, size_t, ssize_t);
+extern int generic_file_buffered_write_one_page(struct address_space *,
+						pgoff_t, struct page *);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern void do_generic_mapping_read(struct address_space *mapping,
mm/filemap.c +61 -0

67 lines not on this page · raw message

author maintainer
#24 lore raw

PATCH 18/37 CacheFiles: Permit the page lock state to be monitored

In reply to David Howells

Add a function to install a monitor on the page lock waitqueue for a particular page, thus allowing the page being unlocked to be detected.

This is used by CacheFiles to detect read completion on a page in the backing filesystem so that it can then copy the data to the waiting netfs page.

---

 include/linux/pagemap.h |    5 +++++
 mm/filemap.c            |   18 ++++++++++++++++++
 2 files changed, 23 insertions(+), 0 deletions(-)
include/linux/pagemap.h +5 -0
index d22e975..eb08fb8 100644
@@ -242,6 +242,11 @@ static inline void wait_on_page_owner_priv_2(struct page *page)
 extern void end_page_owner_priv_2(struct page *page);
 
 /*
+ * Add an arbitrary waiter to a page's wait queue
+ */
+extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+
+/*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *
  * This assumes that two userspace pages are always sufficient.  That's
mm/filemap.c +18 -0
index 6c6cd76..5c0241c 100644
@@ -548,6 +548,24 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page - Page defining the wait queue of interest
+ * @waiter - Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, waiter);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
+/**
  * unlock_page - unlock a locked page
  * @page: the page
  *
author maintainer
#25 lore raw

PATCH 19/37 CacheFiles: Export things for CacheFiles

In reply to David Howells

Export a number of functions for CacheFiles's use.

---

 fs/super.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)
fs/super.c +1 -0
index ceaf2e3..cd199ae 100644
@@ -266,6 +266,7 @@ int fsync_super(struct super_block *sb)
 	__fsync_super(sb);
 	return sync_blockdev(sb->s_bdev);
 }
+EXPORT_SYMBOL_GPL(fsync_super);
 
 /**
  *	generic_shutdown_super	-	common helper for ->kill_sb()
author maintainer
#26 lore raw

PATCH 20/37 CacheFiles: A cache that backs onto a mounted filesystem

In reply to David Howells

Add an FS-Cache cache-backend that permits a mounted filesystem to be used as a backing store for the cache.

CacheFiles uses a userspace daemon to do some of the cache management - such as reaping stale nodes and culling. This is called cachefilesd and lives in /sbin. The source for the daemon can be downloaded from:

http://people.redhat.com/~dhowells/cachefs/cachefilesd.c

And an example configuration from:

http://people.redhat.com/~dhowells/cachefs/cachefilesd.conf

The filesystem and data integrity of the cache are only as good as those of the filesystem providing the backing services. Note that CacheFiles does not attempt to journal anything since the journalling interfaces of the various filesystems are very specific in nature.

CacheFiles creates a proc-file - "/proc/fs/cachefiles" - that is used for communication with the daemon. Only one thing may have this open at once, and whilst it is open, a cache is at least partially in existence. The daemon opens this and sends commands down it to control the cache.

CacheFiles is currently limited to a single cache.

CacheFiles attempts to maintain at least a certain percentage of free space on the filesystem, shrinking the cache by culling the objects it contains to make space if necessary - see the "Cache Culling" section. This means it can be placed on the same medium as a live set of data, and will expand to make use of spare space and automatically contract when the set of data requires more space.

============
REQUIREMENTS
============

The use of CacheFiles and its daemon requires the following features to be available in the system and in the cache filesystem:

- dnotify.

- extended attributes (xattrs).

- openat() and friends.

- bmap() support on files in the filesystem (FIBMAP ioctl).

- The use of bmap() to detect a partial page at the end of the file.

It is strongly recommended that the "dir_index" option is enabled on Ext3 filesystems being used as a cache.

=============
CONFIGURATION
=============

The cache is configured by a script in /etc/cachefilesd.conf. These commands set up cache ready for use. The following script commands are available:

(*) brun <N>%
(*) bcull <N>%
(*) bstop <N>%

Configure the culling limits. Optional. See the section on culling The defaults are 7%, 5% and 1% respectively.

(*) dir <path>

Specify the directory containing the root of the cache. Mandatory.

(*) tag <name>

Specify a tag to FS-Cache to use in distinguishing multiple caches. Optional. The default is "CacheFiles".

(*) debug <mask>

Specify a numeric bitmask to control debugging in the kernel module. Optional. The default is zero (all off).

==================
STARTING THE CACHE
==================

The cache is started by running the daemon. The daemon opens the cache proc file, configures the cache and tells it to begin caching. At that point the cache binds to fscache and the cache becomes live.

The daemon is run as follows:

	/sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>]

The flags are:

(*) -d

Increase the debugging level. This can be specified multiple times and is cumulative with itself.

(*) -s

Send messages to stderr instead of syslog.

(*) -n

Don't daemonise and go into background.

(*) -f <configfile>

Use an alternative configuration file rather than the default one.

===============
THINGS TO AVOID
===============

Do not mount other things within the cache as this will cause problems. The kernel module contains its own very cut-down path walking facility that ignores mountpoints, but the daemon can't avoid them.

Do not create, rename or unlink files and directories in the cache whilst the cache is active, as this may cause the state to become uncertain.

Renaming files in the cache might make objects appear to be other objects (the filename is part of the lookup key).

Do not change or remove the extended attributes attached to cache files by the cache as this will cause the cache state management to get confused.

Do not create files or directories in the cache, lest the cache get confused or serve incorrect data.

Do not chmod files in the cache. The module creates things with minimal permissions to prevent random users being able to access them directly.

=============
CACHE CULLING
=============

The cache may need culling occasionally to make space. This involves discarding objects from the cache that have been used less recently than anything else. Culling is based on the access time of data objects. Empty directories are culled if not in use.

Cache culling is done on the basis of the percentage of blocks available in the underlying filesystem. There are three "limits":

(*) brun

If the amount of available space in the cache rises above this limit, then culling is turned off.

(*) bcull

If the amount of available space in the cache falls below this limit, then culling is started.

(*) bstop

If the amount of available space in the cache falls below this limit, then no further allocation of disk space is permitted until culling has raised the amount above this limit again.

These must be configured thusly:

	0 <= bstop < bcull < brun < 100

Note that these are percentages of available space, and do _not_ appear as 100 minus the percentage displayed by the "df" program.

The userspace daemon scans the cache to build up a table of cullable objects. These are then culled in least recently used order. A new scan of the cache is started as soon as space is made in the table. Objects will be skipped if their atimes have changed or if the kernel module says it is still using them.

===============
CACHE STRUCTURE
===============

The CacheFiles module will create two directories in the directory it was given:

(*) cache/

(*) graveyard/

The active cache objects all reside in the first directory. The CacheFiles kernel module moves any retired or culled objects that it can't simply unlink to the graveyard from which the daemon will actually delete them.

The daemon uses dnotify to monitor the graveyard directory, and will delete anything that appears therein.

The module represents index objects as directories with the filename "I..." or "J...". Note that the "cache/" directory is itself a special index.

Data objects are represented as files if they have no children, or directories if they do. Their filenames all begin "D..." or "E...". If represented as a directory, data objects will have a file in the directory called "data" that actually holds the data.

Special objects are similar to data objects, except their filenames begin "S..." or "T...".

If an object has children, then it will be represented as a directory. Immediately in the representative directory are a collection of directories named for hash values of the child object keys with an '@' prepended. Into this directory, if possible, will be placed the representations of the child objects:

	INDEX     INDEX      INDEX                             DATA FILES
	========= ========== ================================= ================
	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400
	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry
	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry
	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...FP1ry

If the key is so long that it exceeds NAME_MAX with the decorations added on to it, then it will be cut into pieces, the first few of which will be used to make a nest of directories, and the last one of which will be the objects inside the last directory. The names of the intermediate directories will have '+' prepended:

	J1223/@23/+xy...z/+kl...m/Epqr

Note that keys are raw data, and not only may they exceed NAME_MAX in size, they may also contain things like '/' and NUL characters, and so they may not be suitable for turning directly into a filename.

To handle this, CacheFiles will use a suitably printable filename directly and "base-64" encode ones that aren't directly suitable. The two versions of object filenames indicate the encoding:

	OBJECT TYPE	PRINTABLE	ENCODED
	===============	===============	===============
	Index		"I..."		"J..."
	Data		"D..."		"E..."
	Special		"S..."		"T..."

Intermediate directories are always "@" or "+" as appropriate.

Each object in the cache has an extended attribute label that holds the object type ID (required to distinguish special objects) and the auxiliary data from the netfs. The latter is used to detect stale objects in the cache and update or retire them.

Note that CacheFiles will erase from the cache any file it doesn't recognise or any file of an incorrect type (such as a FIFO file or a device file).

This documentation is added by the patch to:

Documentation/filesystems/caching/cachefiles.txt

---

 Documentation/filesystems/caching/cachefiles.txt |  395 ++++++++++
 fs/Kconfig                                       |    1 
 fs/Makefile                                      |    1 
 fs/cachefiles/Kconfig                            |   33 +
 fs/cachefiles/Makefile                           |   18 
 fs/cachefiles/cf-bind.c                          |  289 +++++++
 fs/cachefiles/cf-daemon.c                        |  754 +++++++++++++++++++
 fs/cachefiles/cf-interface.c                     |  445 ++++++++++++
 fs/cachefiles/cf-internal.h                      |  373 ++++++++++
 fs/cachefiles/cf-key.c                           |  159 ++++
 fs/cachefiles/cf-main.c                          |  108 +++
 fs/cachefiles/cf-namei.c                         |  739 +++++++++++++++++++
 fs/cachefiles/cf-proc.c                          |  166 ++++
 fs/cachefiles/cf-rdwr.c                          |  851 ++++++++++++++++++++++
 fs/cachefiles/cf-security.c                      |  105 +++
 fs/cachefiles/cf-xattr.c                         |  292 ++++++++
 security/security.c                              |    2 
 17 files changed, 4731 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/filesystems/caching/cachefiles.txt
 create mode 100644 fs/cachefiles/Kconfig
 create mode 100644 fs/cachefiles/Makefile
 create mode 100644 fs/cachefiles/cf-bind.c
 create mode 100644 fs/cachefiles/cf-daemon.c
 create mode 100644 fs/cachefiles/cf-interface.c
 create mode 100644 fs/cachefiles/cf-internal.h
 create mode 100644 fs/cachefiles/cf-key.c
 create mode 100644 fs/cachefiles/cf-main.c
 create mode 100644 fs/cachefiles/cf-namei.c
 create mode 100644 fs/cachefiles/cf-proc.c
 create mode 100644 fs/cachefiles/cf-rdwr.c
 create mode 100644 fs/cachefiles/cf-security.c
 create mode 100644 fs/cachefiles/cf-xattr.c
Documentation/filesystems/caching/cachefiles.txt new file +395 -0
new file mode 100644
index 0000000..b502cff
@@ -0,0 +1,395 @@
+	       ===============================================
+	       CacheFiles: CACHE ON ALREADY MOUNTED FILESYSTEM
+	       ===============================================
+
+Contents:
+
+ (*) Overview.
+
+ (*) Requirements.
+
+ (*) Configuration.
+
+ (*) Starting the cache.
+
+ (*) Things to avoid.
+
+ (*) Cache culling.
+
+ (*) Cache structure.
+
+ (*) Security model and SELinux.
+
+========
+OVERVIEW
+========
+
+CacheFiles is a caching backend that's meant to use as a cache a directory on
+an already mounted filesystem of a local type (such as Ext3).
+
+CacheFiles uses a userspace daemon to do some of the cache management - such as
+reaping stale nodes and culling.  This is called cachefilesd and lives in
+/sbin.
+
+The filesystem and data integrity of the cache are only as good as those of the
+filesystem providing the backing services.  Note that CacheFiles does not
+attempt to journal anything since the journalling interfaces of the various
+filesystems are very specific in nature.
+
+CacheFiles creates a misc character device - "/dev/cachefiles" - that is used
+to communication with the daemon.  Only one thing may have this open at once,
+and whilst it is open, a cache is at least partially in existence.  The daemon
+opens this and sends commands down it to control the cache.
+
+CacheFiles is currently limited to a single cache.
+
+CacheFiles attempts to maintain at least a certain percentage of free space on
+the filesystem, shrinking the cache by culling the objects it contains to make
+space if necessary - see the "Cache Culling" section.  This means it can be
+placed on the same medium as a live set of data, and will expand to make use of
+spare space and automatically contract when the set of data requires more
+space.
+
+
+============
+REQUIREMENTS
+============
+
+The use of CacheFiles and its daemon requires the following features to be
+available in the system and in the cache filesystem:
+
+	- dnotify.
+
+	- extended attributes (xattrs).
+
+	- openat() and friends.
+
+	- bmap() support on files in the filesystem (FIBMAP ioctl).
+
+	- The use of bmap() to detect a partial page at the end of the file.
+
+It is strongly recommended that the "dir_index" option is enabled on Ext3
+filesystems being used as a cache.
+
+
+=============
+CONFIGURATION
+=============
+
+The cache is configured by a script in /etc/cachefilesd.conf.  These commands
+set up cache ready for use.  The following script commands are available:
+
+ (*) brun <N>%
+ (*) bcull <N>%
+ (*) bstop <N>%
+ (*) frun <N>%
+ (*) fcull <N>%
+ (*) fstop <N>%
+
+	Configure the culling limits.  Optional.  See the section on culling
+	The defaults are 7% (run), 5% (cull) and 1% (stop) respectively.
+
+	The commands beginning with a 'b' are file space (block) limits, those
+	beginning with an 'f' are file count limits.
+
+ (*) dir <path>
+
+	Specify the directory containing the root of the cache.  Mandatory.
+
+ (*) tag <name>
+
+	Specify a tag to FS-Cache to use in distinguishing multiple caches.
+	Optional.  The default is "CacheFiles".
+
+ (*) debug <mask>
+
+	Specify a numeric bitmask to control debugging in the kernel module.
+	Optional.  The default is zero (all off).  The following values can be
+	OR'd into the mask to collect various information:
+
+		1	Turn on trace of function entry (_enter() macros)
+		2	Turn on trace of function exit (_leave() macros)
+		4	Turn on trace of internal debug points (_debug())
+
+	This mask can also be set through sysfs, eg:
+
+		echo 5 >/sys/modules/cachefiles/parameters/debug
+
+
+==================
+STARTING THE CACHE
+==================
+
+The cache is started by running the daemon.  The daemon opens the cache device,
+configures the cache and tells it to begin caching.  At that point the cache
+binds to fscache and the cache becomes live.
+
+The daemon is run as follows:
+
+	/sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>]
+
+The flags are:
+
+ (*) -d
+
+	Increase the debugging level.  This can be specified multiple times and
+	is cumulative with itself.
+
+ (*) -s
+
+	Send messages to stderr instead of syslog.
+
+ (*) -n
+
+	Don't daemonise and go into background.
+
+ (*) -f <configfile>
+
+	Use an alternative configuration file rather than the default one.
+
+
+===============
+THINGS TO AVOID
+===============
+
+Do not mount other things within the cache as this will cause problems.  The
+kernel module contains its own very cut-down path walking facility that ignores
+mountpoints, but the daemon can't avoid them.
+
+Do not create, rename or unlink files and directories in the cache whilst the
+cache is active, as this may cause the state to become uncertain.
+
+Renaming files in the cache might make objects appear to be other objects (the
+filename is part of the lookup key).
+
+Do not change or remove the extended attributes attached to cache files by the
+cache as this will cause the cache state management to get confused.
+
+Do not create files or directories in the cache, lest the cache get confused or
+serve incorrect data.
+
+Do not chmod files in the cache.  The module creates things with minimal
+permissions to prevent random users being able to access them directly.
+
+
+=============
+CACHE CULLING
+=============
+
+The cache may need culling occasionally to make space.  This involves
+discarding objects from the cache that have been used less recently than
+anything else.  Culling is based on the access time of data objects.  Empty
+directories are culled if not in use.
+
+Cache culling is done on the basis of the percentage of blocks and the
+percentage of files available in the underlying filesystem.  There are six
+"limits":
+
+ (*) brun
+ (*) frun
+
+     If the amount of free space and the number of available files in the cache
+     rises above both these limits, then culling is turned off.
+
+ (*) bcull
+ (*) fcull
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then culling is started.
+
+ (*) bstop
+ (*) fstop
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then no further allocation of
+     disk space or files is permitted until culling has raised things above
+     these limits again.
+
+These must be configured thusly:
+
+	0 <= bstop < bcull < brun < 100
+	0 <= fstop < fcull < frun < 100
+
+Note that these are percentages of available space and available files, and do
+_not_ appear as 100 minus the percentage displayed by the "df" program.
+
+The userspace daemon scans the cache to build up a table of cullable objects.
+These are then culled in least recently used order.  A new scan of the cache is
+started as soon as space is made in the table.  Objects will be skipped if
+their atimes have changed or if the kernel module says it is still using them.
+
+
+===============
+CACHE STRUCTURE
+===============
+
+The CacheFiles module will create two directories in the directory it was
+given:
+
+ (*) cache/
+
+ (*) graveyard/
+
+The active cache objects all reside in the first directory.  The CacheFiles
+kernel module moves any retired or culled objects that it can't simply unlink
+to the graveyard from which the daemon will actually delete them.
+
+The daemon uses dnotify to monitor the graveyard directory, and will delete
+anything that appears therein.
+
+
+The module represents index objects as directories with the filename "I..." or
+"J...".  Note that the "cache/" directory is itself a special index.
+
+Data objects are represented as files if they have no children, or directories
+if they do.  Their filenames all begin "D..." or "E...".  If represented as a
+directory, data objects will have a file in the directory called "data" that
+actually holds the data.
+
+Special objects are similar to data objects, except their filenames begin
+"S..." or "T...".
+
+
+If an object has children, then it will be represented as a directory.
+Immediately in the representative directory are a collection of directories
+named for hash values of the child object keys with an '@' prepended.  Into
+this directory, if possible, will be placed the representations of the child
+objects:
+
+	INDEX     INDEX      INDEX                             DATA FILES
+	========= ========== ================================= ================
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...FP1ry
+
+
+If the key is so long that it exceeds NAME_MAX with the decorations added on to
+it, then it will be cut into pieces, the first few of which will be used to
+make a nest of directories, and the last one of which will be the objects
+inside the last directory.  The names of the intermediate directories will have
+'+' prepended:
+
+	J1223/@23/+xy...z/+kl...m/Epqr
+
+
+Note that keys are raw data, and not only may they exceed NAME_MAX in size,
+they may also contain things like '/' and NUL characters, and so they may not
+be suitable for turning directly into a filename.
+
+To handle this, CacheFiles will use a suitably printable filename directly and
+"base-64" encode ones that aren't directly suitable.  The two versions of
+object filenames indicate the encoding:
+
+	OBJECT TYPE	PRINTABLE	ENCODED
+	===============	===============	===============
+	Index		"I..."		"J..."
+	Data		"D..."		"E..."
+	Special		"S..."		"T..."
+
+Intermediate directories are always "@" or "+" as appropriate.
+
+
+Each object in the cache has an extended attribute label that holds the object
+type ID (required to distinguish special objects) and the auxiliary data from
+the netfs.  The latter is used to detect stale objects in the cache and update
+or retire them.
+
+
+Note that CacheFiles will erase from the cache any file it doesn't recognise or
+any file of an incorrect type (such as a FIFO file or a device file).
+
+
+==========================
+SECURITY MODEL AND SELINUX
+==========================
+
+CacheFiles is implemented to deal properly with the LSM security features of
+the Linux kernel and the SELinux facility.
+
+One of the problems that CacheFiles faces is that it is generally acting on
+behalf of a process, and running in that process's context, and that includes a
+security context that is not appropriate for accessing the cache - either
+because the files in the cache are inaccessible to that process, or because if
+the process creates a file in the cache, that file may be inaccessible to other
+processes.
+
+The way CacheFiles works is to temporarily change the security context (fsuid,
+fsgid and actor security label) that the process acts as - without changing the
+security context of the process when it the target of an operation performed by
+some other process (so signalling and suchlike still work correctly).
+
+
+When the CacheFiles module is asked to bind to its cache, it:
+
+ (1) Finds the security label attached to the root cache directory and uses
+     that as the security label with which it will create files.  By default,
+     this is:
+
+	cachefiles_var_t
+
+ (2) Finds the security label of the process which issued the bind request
+     (presumed to be the cachefilesd daemon), which by default will be:
+
+	cachefilesd_t
+
+     and asks LSM to supply a security ID as which it should act given the
+     daemon's label.  By default, this will be:
+
+	cachefiles_kernel_t
+
+     SELinux transitions the daemon's security ID to the module's security ID
+     based on a rule of this form in the policy.
+
+	type_transition <daemon's-ID> kernel_t : process <module's-ID>;
+
+     For instance:
+
+	type_transition cachefilesd_t kernel_t : process cachefiles_kernel_t;
+
+
+The module's security ID gives it permission to create, move and remove files
+and directories in the cache, to find and access directories and files in the
+cache, to set and access extended attributes on cache objects, and to read and
+write files in the cache.
+
+The daemon's security ID gives it only a very restricted set of permissions: it
+may scan directories, stat files and erase files and directories.  It may
+not read or write files in the cache, and so it is precluded from accessing the
+data cached therein; nor is it permitted to create new files in the cache.
+
+
+There are policy source files available in:
+
+	http://people.redhat.com/~dhowells/fscache/cachefilesd-0.8.tar.bz2
+
+and later versions.  In that tarball, see the files:
+
+	cachefilesd.te
+	cachefilesd.fc
+	cachefilesd.if
+
+They are built and installed directly by the RPM.
+
+If a non-RPM based system is being used, then copy the above files to their own
+directory and run:
+
+	make -f /usr/share/selinux/devel/Makefile
+	semodule -i cachefilesd.pp
+
+You will need checkpolicy and selinux-policy-devel installed prior to the
+build.
+
+
+By default, the cache is located in /var/fscache, but if it is desirable that
+it should be elsewhere, than either the above policy files must be altered, or
+an auxiliary policy must be installed to label the alternate location of the
+cache.
+
+For instructions on how to add an auxiliary policy to enable the cache to be
+located elsewhere when SELinux is in enforcing mode, please see:
+
+	/usr/share/doc/cachefilesd-*/move-cache.txt
+
+When the cachefilesd rpm is installed; alternatively, the document can be found
+in the sources.
fs/Kconfig +1 -0
index 80264c0..c42ec50 100644
@@ -621,6 +621,7 @@ config GENERIC_ACL
 menu "Caches"
 
 source "fs/fscache/Kconfig"
+source "fs/cachefiles/Kconfig"
 
 endmenu
 
fs/Makefile +1 -0
index 11e47bf..0830806 100644
@@ -117,6 +117,7 @@ obj-$(CONFIG_AFS_FS)		+= afs/
 obj-$(CONFIG_BEFS_FS)		+= befs/
 obj-$(CONFIG_HOSTFS)		+= hostfs/
 obj-$(CONFIG_HPPFS)		+= hppfs/
+obj-$(CONFIG_CACHEFILES)	+= cachefiles/
 obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
fs/cachefiles/Kconfig new file +33 -0
new file mode 100644
index 0000000..ddbdd85
@@ -0,0 +1,33 @@
+
+config CACHEFILES
+	tristate "Filesystem caching on files"
+	depends on FSCACHE
+	help
+	  This permits use of a mounted filesystem as a cache for other
+	  filesystems - primarily networking filesystems - thus allowing fast
+	  local disk to enhance the speed of slower devices.
+
+	  See Documentation/filesystems/caching/cachefiles.txt for more
+	  information.
+
+config CACHEFILES_DEBUG
+	bool "Debug CacheFiles"
+	depends on CACHEFILES
+	help
+	  This permits debugging to be dynamically enabled in the filesystem
+	  caching on files module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/cachefiles/parameter/debug or
+	  by including a debugging specifier in /etc/cachefilesd.conf.
+
+config CACHEFILES_HISTOGRAM
+	bool "Gather latency information on CacheFiles"
+	depends on CACHEFILES && FSCACHE_PROC
+	help
+
+	  This option causes latency information to be gathered on CacheFiles
+	  operation and exported through file:
+
+		/proc/fs/fscache/cachefiles/histogram
+
+	  See Documentation/filesystems/caching/cachefiles.txt for more
+	  information.
fs/cachefiles/Makefile new file +18 -0
new file mode 100644
index 0000000..8a9c1bd
@@ -0,0 +1,18 @@
+#
+# Makefile for caching in a mounted filesystem
+#
+
+cachefiles-y := \
+	cf-bind.o \
+	cf-daemon.o \
+	cf-interface.o \
+	cf-key.o \
+	cf-main.o \
+	cf-namei.o \
+	cf-rdwr.o \
+	cf-security.o \
+	cf-xattr.o
+
+cachefiles-$(CONFIG_CACHEFILES_HISTOGRAM) += cf-proc.o
+
+obj-$(CONFIG_CACHEFILES) := cachefiles.o
fs/cachefiles/cf-bind.c new file +289 -0

289 lines not on this page · raw message

fs/cachefiles/cf-daemon.c new file +754 -0

754 lines not on this page · raw message

fs/cachefiles/cf-interface.c new file +445 -0

445 lines not on this page · raw message

fs/cachefiles/cf-internal.h new file +373 -0

373 lines not on this page · raw message

fs/cachefiles/cf-key.c new file +159 -0

159 lines not on this page · raw message

fs/cachefiles/cf-main.c new file +108 -0

108 lines not on this page · raw message

fs/cachefiles/cf-namei.c new file +739 -0

412 lines not on this page · raw message

fs/cachefiles/cf-proc.c new file +166 -0

166 lines not on this page · raw message

fs/cachefiles/cf-rdwr.c new file +851 -0

851 lines not on this page · raw message

fs/cachefiles/cf-security.c new file +105 -0

105 lines not on this page · raw message

fs/cachefiles/cf-xattr.c new file +292 -0

292 lines not on this page · raw message

security/security.c +2 -0
index e7345e1..d860a70 100644

Lines of this file are not shown. View the raw message.

The rest of this diff is not shown. View the raw message.

Part of the diff is not shown here. View the raw message.

author maintainer
#27 lore raw

PATCH 21/37 NFS: Add comment banners to some NFS functions

In reply to David Howells

Add comment banners to some NFS functions so that they can be modified by the NFS fscache patches for further information.

---

 fs/nfs/file.c |   26 ++++++++++++++++++++++++++
 1 files changed, 26 insertions(+), 0 deletions(-)
fs/nfs/file.c +26 -0
index ef57a5a..26a073b 100644
@@ -354,6 +354,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
+/*
+ * Partially or wholly invalidate a page
+ * - Release the private state associated with a page if undergoing complete
+ *   page invalidation
+ * - Called if either PG_private or PG_private_2 is set on the page
+ * - Caller holds page lock
+ */
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
 {
 	if (offset != 0)
@@ -362,12 +369,26 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	nfs_wb_page_cancel(page->mapping->host, page);
 }
 
+/*
+ * Attempt to release the private state associated with a page
+ * - Called if either PG_private or PG_private_2 is set on the page
+ * - Caller holds page lock
+ * - Return true (may release page) or false (may not)
+ */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
 	/* If PagePrivate() is set, then the page is not freeable */
 	return 0;
 }
 
+/*
+ * Attempt to clear the private state associated with a page when an error
+ * occurs that requires the cached contents of an inode to be written back or
+ * destroyed
+ * - Called if either PG_private or PG_private_2 is set on the page
+ * - Caller holds page lock
+ * - Return 0 if successful, -error otherwise
+ */
 static int nfs_launder_page(struct page *page)
 {
 	return nfs_wb_page(page->mapping->host, page);
@@ -389,6 +410,11 @@ const struct address_space_operations nfs_file_aops = {
 	.launder_page = nfs_launder_page,
 };
 
+/*
+ * Notification that a PTE pointing to an NFS page is about to be made
+ * writable, implying that someone is about to modify the page through a
+ * shared-writable mapping
+ */
 static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 {
 	struct file *filp = vma->vm_file;
author maintainer
#28 lore raw

PATCH 22/37 NFS: Add FS-Cache option bit and debug bit

In reply to David Howells

Add FS-Cache option bit to nfs_server struct. This is set to indicate local on-disk caching is enabled for a particular superblock.

Also add debug bit for local caching operations.

---

 include/linux/nfs_fs.h    |    1 +
 include/linux/nfs_fs_sb.h |    2 ++
 2 files changed, 3 insertions(+), 0 deletions(-)
include/linux/nfs_fs.h +1 -0
index a69ba80..14894c9 100644
@@ -578,6 +578,7 @@ extern void * nfs_root_data(void);
 #define NFSDBG_CALLBACK		0x0100
 #define NFSDBG_CLIENT		0x0200
 #define NFSDBG_MOUNT		0x0400
+#define NFSDBG_FSCACHE		0x0800
 #define NFSDBG_ALL		0xFFFF
 
 #ifdef __KERNEL__
include/linux/nfs_fs_sb.h +2 -0
index 3423c67..e7c4cdd 100644
@@ -99,6 +99,8 @@ struct nfs_server {
 	unsigned int		acdirmin;
 	unsigned int		acdirmax;
 	unsigned int		namelen;
+	unsigned int		options;	/* extra options enabled by mount */
+#define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
 
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */
author maintainer
#29 lore raw

PATCH 23/37 NFS: Permit local filesystem caching to be enabled for NFS

In reply to David Howells

Permit local filesystem caching to be enabled for NFS in the kernel configuration.

---

 fs/Kconfig |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)
fs/Kconfig +8 -0
index c42ec50..fa8e978 100644
@@ -1644,6 +1644,14 @@ config NFS_V4
 
 	  If unsure, say N.
 
+config NFS_FSCACHE
+	bool "Provide NFS client caching support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
+	help
+	  Say Y here if you want NFS data to be cached locally on disc through
+	  the general filesystem cache manager
+
 config NFS_DIRECTIO
 	bool "Allow direct I/O on NFS files"
 	depends on NFS_FS
author maintainer
#30 lore raw

PATCH 24/37 NFS: Register NFS for caching and retrieve the top-level index

In reply to David Howells

Register NFS for caching and retrieve the top-level cache index object cookie.

---

 fs/nfs/Makefile        |    1 +
 fs/nfs/fscache-index.c |   53 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h       |   35 ++++++++++++++++++++++++++++++++
 fs/nfs/inode.c         |    8 +++++++
 4 files changed, 97 insertions(+), 0 deletions(-)
 create mode 100644 fs/nfs/fscache-index.c
 create mode 100644 fs/nfs/fscache.h
fs/nfs/Makefile +1 -0
index df0f41e..6d7176d 100644
@@ -16,3 +16,4 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   nfs4namespace.o
 nfs-$(CONFIG_NFS_DIRECTIO) += direct.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache-index.o
fs/nfs/fscache-index.c new file +53 -0

53 lines not on this page · raw message

fs/nfs/fscache.h new file +35 -0
new file mode 100644
index 0000000..75e5a03
@@ -0,0 +1,35 @@
+/* NFS filesystem cache interface definitions
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells ([email protected])
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _NFS_FSCACHE_H
+#define _NFS_FSCACHE_H
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+
+#ifdef CONFIG_NFS_FSCACHE
+#include <linux/fscache.h>
+
+/*
+ * fscache-index.c
+ */
+extern struct fscache_netfs nfs_cache_netfs;
+
+extern int nfs_fscache_register(void);
+extern void nfs_fscache_unregister(void);
+
+#else /* CONFIG_NFS_FSCACHE */
+static inline int nfs_fscache_register(void) { return 0; }
+static inline void nfs_fscache_unregister(void) {}
+
+#endif /* CONFIG_NFS_FSCACHE */
+#endif /* _NFS_FSCACHE_H */
fs/nfs/inode.c +8 -0
index 966a885..7254d5c 100644
@@ -46,6 +46,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -1222,6 +1223,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_fscache_register();
+	if (err < 0)
+		goto out6;
+
 	err = nfs_fs_proc_init();
 	if (err)
 		goto out5;
@@ -1268,6 +1273,8 @@ out3:
 out4:
 	nfs_fs_proc_exit();
 out5:
+	nfs_fscache_unregister();
+out6:
 	return err;
 }
 
@@ -1278,6 +1285,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_readpagecache();
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
+	nfs_fscache_unregister();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister("nfs");
 #endif
author maintainer
#31 lore raw

PATCH 25/37 NFS: Define and create server-level objects

In reply to David Howells

Define and create server-level cache index objects (as managed by nfs_client structs).

Each server object is created in the NFS top-level index object and is itself an index into which superblock-level objects are inserted.

Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible.

The server object key is a sequence consisting of:

(1) NFS version

(2) Server address family (eg: AF_INET or AF_INET6)

(3) Server port.

(4) Server IP address.

The key blob is of variable length, depending on the length of (4).

The server object is given no coherency data to carry in the auxiliary data permitted by the cache.

---

 fs/nfs/Makefile           |    2 +
 fs/nfs/client.c           |    5 +++
 fs/nfs/fscache-index.c    |   65 +++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.c          |   52 ++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h          |   10 +++++++
 include/linux/nfs_fs_sb.h |    4 +++
 6 files changed, 137 insertions(+), 1 deletions(-)
 create mode 100644 fs/nfs/fscache.c
fs/nfs/Makefile +1 -1
index 6d7176d..d848c97 100644
@@ -16,4 +16,4 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   nfs4namespace.o
 nfs-$(CONFIG_NFS_DIRECTIO) += direct.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
-nfs-$(CONFIG_NFS_FSCACHE) += fscache-index.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
fs/nfs/client.c +5 -0
index c5c0175..51e9346 100644
@@ -45,6 +45,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -151,6 +152,8 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
 #endif
 
+	nfs_fscache_get_client_cookie(clp);
+
 	return clp;
 
 error_3:
@@ -182,6 +185,8 @@ static void nfs_free_client(struct nfs_client *clp)
 
 	nfs4_shutdown_client(clp);
 
+	nfs_fscache_release_client_cookie(clp);
+
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
fs/nfs/fscache-index.c +65 -0

68 lines not on this page · raw message

fs/nfs/fscache.c new file +52 -0

52 lines not on this page · raw message

fs/nfs/fscache.h +10 -0
index 75e5a03..df6dbb4 100644
@@ -23,13 +23,23 @@
  * fscache-index.c
  */
 extern struct fscache_netfs nfs_cache_netfs;
+extern const struct fscache_cookie_def nfs_cache_server_index_def;
 
 extern int nfs_fscache_register(void);
 extern void nfs_fscache_unregister(void);
 
+/*
+ * fscache.c
+ */
+extern void nfs_fscache_get_client_cookie(struct nfs_client *);
+extern void nfs_fscache_release_client_cookie(struct nfs_client *);
+
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
 
+static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
+static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
+
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */
include/linux/nfs_fs_sb.h +4 -0
index e7c4cdd..8d23dcb 100644
@@ -68,6 +68,10 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	unsigned char		cl_id_uniquifier;
 #endif
+
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;	/* client index cache cookie */
+#endif
 };
 
 /*
author maintainer
#32 lore raw

PATCH 26/37 NFS: Define and create superblock-level objects

In reply to David Howells

Define and create superblock-level cache index objects (as managed by nfs_server structs).

Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted.

Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible.

The superblock object key is a sequence consisting of:

(1) Certain superblock s_flags.

(2) Various connection parameters that serve to distinguish superblocks for

     sget().

(3) The volume FSID.

(4) The security flavour.

(5) The uniquifier length.

(6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier.

The key blob is of variable length, depending on the length of (6).

The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent.

This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced.

---

 fs/nfs/fscache-index.c    |   34 +++++++++++++
 fs/nfs/fscache.c          |  116 +++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h          |   49 +++++++++++++++++++
 fs/nfs/internal.h         |    3 +
 fs/nfs/super.c            |    8 ++-
 include/linux/nfs_fs_sb.h |    5 ++
 6 files changed, 213 insertions(+), 2 deletions(-)
fs/nfs/fscache-index.c +34 -0
index 25ac4a1..b5a52e3 100644
@@ -116,3 +116,37 @@ const struct fscache_cookie_def nfs_cache_server_index_def = {
 	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
 	.get_key	= nfs_server_get_key,
 };
+
+/*
+ * Generate a key to describe a superblock key in the main NFS index
+ */
+static uint16_t nfs_super_get_key(const void *cookie_netfs_data,
+				  void *buffer, uint16_t bufmax)
+{
+	const struct nfs_fscache_key *key;
+	const struct nfs_server *nfss = cookie_netfs_data;
+	uint16_t len;
+
+	key = nfss->fscache_key;
+	len = sizeof(key->key) + key->key.uniq_len;
+	if (len > bufmax) {
+		len = 0;
+	} else {
+		memcpy(buffer, &key->key, sizeof(key->key));
+		memcpy(buffer + sizeof(key->key),
+		       key->key.uniquifier, key->key.uniq_len);
+	}
+
+	return len;
+}
+
+/*
+ * Define the superblock object for FS-Cache.  This is used to describe a
+ * superblock object to fscache_acquire_cookie().  It is keyed by all the NFS
+ * parameters that might cause a separate superblock.
+ */
+const struct fscache_cookie_def nfs_cache_super_index_def = {
+	.name		= "NFS.super",
+	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= nfs_super_get_key,
+};
fs/nfs/fscache.c +116 -0

125 lines not on this page · raw message

fs/nfs/fscache.h +49 -0

70 lines not on this page · raw message

fs/nfs/internal.h +3 -0
index 0f56196..e49cb6e 100644
@@ -4,6 +4,8 @@
 
 #include <linux/mount.h>
 
+#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
+
 struct nfs_string;
 
 /* Maximum number of readahead requests
@@ -40,6 +42,7 @@ struct nfs_parsed_mount_data {
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
 	char			*client_address;
+	char			*fscache_uniq;
 
 	struct {
 		struct sockaddr_storage	address;
fs/nfs/super.c +6 -2
index 7f4505f..437c3dd 100644
@@ -59,6 +59,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -1353,8 +1354,6 @@ static void nfs_clone_super(struct super_block *sb,
  	nfs_initialise_sb(sb);
 }
 
-#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
-
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
 {
 	const struct nfs_server *a = s->s_fs_info;
@@ -1503,6 +1502,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs_fill_super(s, &data);
+		nfs_fscache_get_super_cookie(s, &data);
 	}
 
 	mntroot = nfs_get_root(s, &mntfh);
@@ -1519,6 +1519,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 out:
 	kfree(data.nfs_server.hostname);
 	kfree(data.mount_server.hostname);
+	kfree(data.fscache_uniq);
 	return error;
 
 out_err_nosb:
@@ -1539,6 +1540,7 @@ static void nfs_kill_super(struct super_block *s)
 	struct nfs_server *server = NFS_SB(s);
 
 	kill_anon_super(s);
+	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
 
@@ -1877,6 +1879,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs4_fill_super(s);
+		nfs_fscache_get_super_cookie(s, &data);
 	}
 
 	mntroot = nfs4_get_root(s, &mntfh);
@@ -1894,6 +1897,7 @@ out:
 	kfree(data.client_address);
 	kfree(data.nfs_server.export_path);
 	kfree(data.nfs_server.hostname);
+	kfree(data.fscache_uniq);
 	return error;
 
 out_free:
include/linux/nfs_fs_sb.h +5 -0
index 8d23dcb..fd592cc 100644
@@ -110,6 +110,11 @@ struct nfs_server {
 	__u64			maxfilesize;	/* maximum file size */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	dev_t			s_dev;		/* superblock dev numbers */
+ 
+#ifdef CONFIG_NFS_FSCACHE
+	struct nfs_fscache_key	*fscache_key;	/* unique key for superblock */
+	struct fscache_cookie	*fscache;	/* superblock cookie */
+#endif
 
 #ifdef CONFIG_NFS_V4
 	u32			attr_bitmask[2];/* V4 bitmask representing the set

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#33 lore raw

PATCH 27/37 NFS: Define and create inode-level cache objects

In reply to David Howells

Define and create inode-level cache data storage objects (as managed by nfs_inode structs).

Each inode-level object is created in a superblock-level index object and is itself a data storage object into which pages from the inode are stored.

The inode object key is the NFS file handle for the inode.

The inode object is given coherency data to carry in the auxiliary data permitted by the cache. This is a sequence made up of:

(1) i_mtime from the NFS inode.

(2) i_ctime from the NFS inode.

(3) i_size from the NFS inode.

As the cache is a persistent cache, the auxiliary data is checked when a new NFS in-memory inode is set up that matches an already existing data storage object in the cache. If the coherency data is the same, the on-disk object is retained and used; if not, it is scrapped and a new one created.

---

 fs/nfs/fscache-index.c |  112 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h       |    1 
 2 files changed, 113 insertions(+), 0 deletions(-)
fs/nfs/fscache-index.c +112 -0
index b5a52e3..c3c63fa 100644
@@ -150,3 +150,115 @@ const struct fscache_cookie_def nfs_cache_super_index_def = {
 	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
 	.get_key	= nfs_super_get_key,
 };
+
+/*
+ * Definition of the auxiliary data attached to NFS inode storage objects
+ * within the cache.
+ *
+ * The contents of this struct are recorded in the on-disk local cache in the
+ * auxiliary data attached to the data storage object backing an inode.  This
+ * permits coherency to be managed when a new inode binds to an already extant
+ * cache object.
+ */
+struct nfs_cache_inode_auxdata {
+	struct timespec	mtime;
+	struct timespec	ctime;
+	loff_t		size;
+};
+
+/*
+ * Generate a key to describe an NFS inode in an NFS server's index
+ */
+static uint16_t nfs_cache_inode_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+	uint16_t nsize;
+
+	/* use the inode's NFS filehandle as the key */
+	nsize = nfsi->fh.size;
+	memcpy(buffer, nfsi->fh.data, nsize);
+	return nsize;
+}
+
+/*
+ * Get certain file attributes from the netfs data
+ * - This function can be absent for an index
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static void nfs_cache_inode_get_attr(const void *cookie_netfs_data, uint64_t *size)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	*size = nfsi->vfs_inode.i_size;
+}
+
+/*
+ * Get the auxiliary data from netfs data
+ * - This function can be absent if the index carries no state data
+ * - Should store the auxiliary data in the buffer
+ * - Should return the amount of amount stored
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static uint16_t nfs_cache_inode_get_aux(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
+{
+	struct nfs_cache_inode_auxdata auxdata;
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (bufmax > sizeof(auxdata))
+		bufmax = sizeof(auxdata);
+
+	memcpy(buffer, &auxdata, bufmax);
+	return bufmax;
+}
+
+/*
+ * Consult the netfs about the state of an object
+ * - This function can be absent if the index carries no state data
+ * - The netfs data from the cookie being used as the target is
+ *   presented, as is the auxiliary data
+ */
+static enum fscache_checkaux nfs_cache_inode_check_aux(void *cookie_netfs_data,
+						       const void *data,
+						       uint16_t datalen)
+{
+	struct nfs_cache_inode_auxdata auxdata;
+	struct nfs_inode *nfsi = cookie_netfs_data;
+
+	if (datalen > sizeof(auxdata))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (memcmp(data, &auxdata, datalen) != 0)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+/*
+ * Define the inode object for FS-Cache.  This is used to describe an inode
+ * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
+ * an inode.
+ *
+ * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime
+ * held in the cache auxiliary data for the data storage object with those in
+ * the inode struct in memory.
+ */
+const struct fscache_cookie_def nfs_cache_inode_object_def = {
+	.name		= "NFS.fh",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= nfs_cache_inode_get_key,
+	.get_attr	= nfs_cache_inode_get_attr,
+	.get_aux	= nfs_cache_inode_get_aux,
+	.check_aux	= nfs_cache_inode_check_aux,
+};
fs/nfs/fscache.h +1 -0
index 242cc07..7dcdf32 100644
@@ -62,6 +62,7 @@ struct nfs_fscache_key {
 extern struct fscache_netfs nfs_cache_netfs;
 extern const struct fscache_cookie_def nfs_cache_server_index_def;
 extern const struct fscache_cookie_def nfs_cache_super_index_def;
+extern const struct fscache_cookie_def nfs_cache_inode_object_def;
 
 extern int nfs_fscache_register(void);
 extern void nfs_fscache_unregister(void);
author maintainer
#34 lore raw

PATCH 28/37 NFS: Use local disk inode cache

In reply to David Howells

Bind data storage objects in the local cache to NFS inodes.

---

 fs/nfs/fscache.c       |  131 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h       |   19 +++++++
 fs/nfs/inode.c         |   39 ++++++++++++--
 include/linux/nfs_fs.h |   10 ++++
 4 files changed, 193 insertions(+), 6 deletions(-)
fs/nfs/fscache.c +131 -0
index cbd09f0..c0e0320 100644
@@ -166,3 +166,134 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
 		nfss->fscache_key = NULL;
 	}
 }
+
+/*
+ * Initialise the per-inode cache cookie pointer for an NFS inode.
+ */
+void nfs_fscache_init_inode_cookie(struct inode *inode)
+{
+	NFS_I(inode)->fscache = NULL;
+	if (S_ISREG(inode->i_mode))
+		set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
+/*
+ * Get the per-inode cache cookie for an NFS inode.
+ */
+void nfs_fscache_enable_inode_cookie(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (nfsi->fscache || !NFS_FSCACHE(inode))
+		return;
+
+	if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
+		nfsi->fscache = fscache_acquire_cookie(
+			NFS_SB(sb)->fscache,
+			&nfs_cache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
+			 sb, nfsi, nfsi->fscache);
+	}
+}
+
+/*
+ * Release a per-inode cookie.
+ */
+void nfs_fscache_release_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 0);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Retire a per-inode cookie, destroying the data attached to it.
+ */
+void nfs_fscache_zap_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 1);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Turn off the cache with regard to a per-inode cookie if opened for writing,
+ * invalidating all the pages in the page cache relating to the associated
+ * inode to clear the per-page caching.
+ */
+void nfs_fscache_disable_inode_cookie(struct inode *inode)
+{
+	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+
+	if (NFS_I(inode)->fscache) {
+		dfprintk(FSCACHE,
+			 "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
+
+		/* Need to invalidate any mapped pages that were read in before
+		 * turning off the cache.
+		 */
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2(inode->i_mapping);
+
+		nfs_fscache_zap_inode_cookie(inode);
+	}
+}
+
+/*
+ * Decide if we should enable or disable local caching for this inode.
+ * - For now, with NFS, only regular files that are open read-only will be able
+ *   to use the cache.
+ */
+void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
+{
+	if (NFS_FSCACHE(inode)) {
+		if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+			nfs_fscache_disable_inode_cookie(inode);
+		else
+			nfs_fscache_enable_inode_cookie(inode);
+	}
+}
+
+/*
+ * Replace a per-inode cookie due to revalidation detecting a file having
+ * changed on the server.
+ */
+void nfs_fscache_renew_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs_server *nfss = NFS_SERVER(inode);
+	struct fscache_cookie *old = nfsi->fscache;
+
+	if (nfsi->fscache) {
+		/* retire the current fscache cache and get a new one */
+		fscache_relinquish_cookie(nfsi->fscache, 1);
+
+		nfsi->fscache = fscache_acquire_cookie(
+			nfss->nfs_client->fscache,
+			&nfs_cache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE,
+			 "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
+			 nfss, nfsi, old, nfsi->fscache);
+	}
+}
+
+/*
+ * Update the filesize associated with a per-inode cookie.
+ */
+void nfs_fscache_attr_changed(struct inode *inode)
+{
+	fscache_attr_changed(NFS_I(inode)->fscache);
+}
fs/nfs/fscache.h +19 -0
index 7dcdf32..d730ec8 100644
@@ -77,6 +77,15 @@ extern void nfs_fscache_get_super_cookie(struct super_block *,
 					 struct nfs_parsed_mount_data *);
 extern void nfs_fscache_release_super_cookie(struct super_block *);
 
+extern void nfs_fscache_init_inode_cookie(struct inode *);
+extern void nfs_fscache_enable_inode_cookie(struct inode *);
+extern void nfs_fscache_release_inode_cookie(struct inode *);
+extern void nfs_fscache_zap_inode_cookie(struct inode *);
+extern void nfs_fscache_disable_inode_cookie(struct inode *);
+extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
+extern void nfs_fscache_renew_inode_cookie(struct inode *);
+extern void nfs_fscache_attr_changed(struct inode *);
+
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
@@ -91,5 +100,15 @@ static inline void nfs_fscache_get_super_cookie(
 }
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
 
+static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_enable_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_release_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_zap_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_renew_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_disable_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
+					     struct file *filp) {}
+static inline void nfs_fscache_attr_changed(struct inode *inode) {}
+
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */
fs/nfs/inode.c +33 -6
index 7254d5c..eafad13 100644
@@ -112,6 +112,7 @@ void nfs_clear_inode(struct inode *inode)
 	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
 	nfs_zap_acl_cache(inode);
 	nfs_access_zap_cache(inode);
+	nfs_fscache_release_inode_cookie(inode);
 }
 
 /**
@@ -331,6 +332,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 		nfsi->access_cache = RB_ROOT;
 
+		nfs_fscache_init_inode_cookie(inode);
+
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
@@ -619,6 +622,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 	ctx->mode = filp->f_mode;
 	nfs_file_set_open_context(filp, ctx);
 	put_nfs_open_context(ctx);
+	nfs_fscache_set_inode_cookie(inode, filp);
 	return 0;
 }
 
@@ -679,7 +683,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 			 (long long)NFS_FILEID(inode), status);
 		goto out;
 	}
-	spin_unlock(&inode->i_lock);
+	if (nfsi->cache_validity & NFS_INO_INVALID_FSCACHE_ATTR) {
+		nfsi->cache_validity &= ~NFS_INO_INVALID_FSCACHE_ATTR;
+		spin_unlock(&inode->i_lock);
+		nfs_fscache_attr_changed(inode);
+	} else {
+		spin_unlock(&inode->i_lock);
+	}
 
 	if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
 		nfs_zap_acl_cache(inode);
@@ -735,6 +745,7 @@ static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_spa
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
+	nfs_fscache_renew_inode_cookie(inode);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -911,7 +922,13 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 	else
 		status = nfs_check_inode_attributes(inode, fattr);
 
-	spin_unlock(&inode->i_lock);
+	if (nfsi->cache_validity & NFS_INO_INVALID_FSCACHE_ATTR) {
+		nfsi->cache_validity &= ~NFS_INO_INVALID_FSCACHE_ATTR;
+		spin_unlock(&inode->i_lock);
+		nfs_fscache_attr_changed(inode);
+	} else {
+		spin_unlock(&inode->i_lock);
+	}
 	return status;
 }
 
@@ -932,12 +949,19 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	bool update_fscache = false;
 
 	spin_lock(&inode->i_lock);
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	if (S_ISDIR(inode->i_mode))
 		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+	if (nfsi->cache_validity & NFS_INO_INVALID_FSCACHE_ATTR) {
+		nfsi->cache_validity &= ~NFS_INO_INVALID_FSCACHE_ATTR;
+		update_fscache = true;
+	}
 	spin_unlock(&inode->i_lock);
+	if (update_fscache)
+		nfs_fscache_attr_changed(inode);
 	return nfs_refresh_inode(inode, fattr);
 }
 
@@ -1025,7 +1049,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
 			dprintk("NFS: mtime change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA |
+				NFS_INO_INVALID_FSCACHE_ATTR;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 		}
@@ -1035,7 +1060,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	} else if (nfsi->change_attr != fattr->change_attr) {
 		dprintk("NFS: change_attr change on server for file %s/%ld\n",
 				inode->i_sb->s_id, inode->i_ino);
-		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA |
+			NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL |
+			NFS_INO_INVALID_FSCACHE_ATTR;
 		if (S_ISDIR(inode->i_mode))
 			nfs_force_lookup_revalidate(inode);
 	}
@@ -1048,13 +1075,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		 * the file grown beyond our last write? */
 		if (nfsi->npages == 0 || new_isize > cur_isize) {
 			inode->i_size = new_isize;
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA |
+				NFS_INO_INVALID_FSCACHE_ATTR;
 		}
 		dprintk("NFS: isize change on server for file %s/%ld\n",
 				inode->i_sb->s_id, inode->i_ino);
 	}
 
-
 	memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
include/linux/nfs_fs.h +10 -0
index 14894c9..d9adb53 100644
@@ -174,6 +174,9 @@ struct nfs_inode {
 	int			 delegation_state;
 	struct rw_semaphore	rwsem;
 #endif /* CONFIG_NFS_V4*/
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;
+#endif
 	struct inode		vfs_inode;
 };
 
@@ -187,6 +190,7 @@ struct nfs_inode {
 #define NFS_INO_INVALID_ACL	0x0010		/* cached acls are invalid */
 #define NFS_INO_REVAL_PAGECACHE	0x0020		/* must revalidate pagecache */
 #define NFS_INO_REVAL_FORCED	0x0040		/* force revalidation ignoring a delegation */
+#define NFS_INO_INVALID_FSCACHE_ATTR	0x0080	/* local cache attributes are invalid */
 
 /*
  * Bit offsets in flags field
@@ -195,6 +199,7 @@ struct nfs_inode {
 #define NFS_INO_ADVISE_RDPLUS	(1)		/* advise readdirplus */
 #define NFS_INO_STALE		(2)		/* possible stale inode */
 #define NFS_INO_ACL_LRU_SET	(3)		/* Inode is on the LRU list */
+#define NFS_INO_FSCACHE		(4)		/* inode can be cached by FS-Cache */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
@@ -248,6 +253,11 @@ static inline int NFS_STALE(const struct inode *inode)
 	return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
+static inline int NFS_FSCACHE(const struct inode *inode)
+{
+	return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
 static inline __u64 NFS_FILEID(const struct inode *inode)
 {
 	return NFS_I(inode)->fileid;
author maintainer
#35 lore raw

PATCH 29/37 NFS: Invalidate FsCache page flags when cache removed

In reply to David Howells

Invalidate the FsCache page flags on the pages belonging to an inode when the cache backing that NFS inode is removed.

This allows a live cache to be withdrawn.

---

 fs/nfs/fscache-index.c |   40 ++++++++++++++++++++++++++++++++++++++++
 1 files changed, 40 insertions(+), 0 deletions(-)
fs/nfs/fscache-index.c +40 -0
index c3c63fa..eec8e7e 100644
@@ -246,6 +246,45 @@ static enum fscache_checkaux nfs_cache_inode_check_aux(void *cookie_netfs_data,
 }
 
 /*
+ * Indication from FS-Cache that the cookie is no longer cached
+ * - This function is called when the backing store currently caching a cookie
+ *   is removed
+ * - The netfs should use this to clean up any markers indicating cached pages
+ * - This is mandatory for any object that may have data
+ */
+static void nfs_cache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct nfs_inode *nfsi = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi);
+
+	for (;;) {
+		/* grab a bunch of pages to unmark */
+		nr_pages = pagevec_lookup(&pvec,
+					  nfsi->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+/*
  * Define the inode object for FS-Cache.  This is used to describe an inode
  * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
  * an inode.
@@ -261,4 +300,5 @@ const struct fscache_cookie_def nfs_cache_inode_object_def = {
 	.get_attr	= nfs_cache_inode_get_attr,
 	.get_aux	= nfs_cache_inode_get_aux,
 	.check_aux	= nfs_cache_inode_check_aux,
+	.now_uncached	= nfs_cache_inode_now_uncached,
 };

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#36 lore raw

PATCH 30/37 NFS: Add some new I/O event counters for FS-Cache events

In reply to David Howells

Add some new NFS I/O event counters for FS-Cache events. They have to be added as byte counters because I may need to be able to increase the numbers by more than 1 at a time.

---

 fs/nfs/iostat.h |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)
fs/nfs/iostat.h +7 -0
index 6350ecb..0e3b170 100644
@@ -60,6 +60,13 @@ enum nfs_stat_bytecounters {
 	NFSIOS_SERVERWRITTENBYTES,
 	NFSIOS_READPAGES,
 	NFSIOS_WRITEPAGES,
+#ifdef CONFIG_NFS_FSCACHE
+	NFSIOS_FSCACHE_READ_OK,
+	NFSIOS_FSCACHE_READ_FAIL,
+	NFSIOS_FSCACHE_WRITE_OK,
+	NFSIOS_FSCACHE_WRITE_FAIL,
+	NFSIOS_FSCACHE_UNCACHE,
+#endif
 	__NFSIOS_BYTESMAX,
 };
 

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#37 lore raw

PATCH 31/37 NFS: FS-Cache page management

In reply to David Howells

FS-Cache page management for NFS. This includes hooking the releasing and invalidation of pages marked with PG_fscache (aka PG_private_2) and waiting for completion of the write-to-cache flag (PG_fscache_write aka PG_owner_priv_2).

---

 fs/nfs/file.c    |   17 +++++++++++++----
 fs/nfs/fscache.c |   49 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h |   22 ++++++++++++++++++++++
 3 files changed, 84 insertions(+), 4 deletions(-)
fs/nfs/file.c +13 -4
index 26a073b..60db3ea 100644
@@ -35,6 +35,7 @@
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
@@ -358,7 +359,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
  * Partially or wholly invalidate a page
  * - Release the private state associated with a page if undergoing complete
  *   page invalidation
- * - Called if either PG_private or PG_private_2 is set on the page
+ * - Called if either PG_private or PG_fscache is set on the page
  * - Caller holds page lock
  */
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
@@ -367,30 +368,35 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 		return;
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_page_cancel(page->mapping->host, page);
+
+	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
 
 /*
  * Attempt to release the private state associated with a page
- * - Called if either PG_private or PG_private_2 is set on the page
+ * - Called if either PG_private or PG_fscache is set on the page
  * - Caller holds page lock
  * - Return true (may release page) or false (may not)
  */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
 	/* If PagePrivate() is set, then the page is not freeable */
-	return 0;
+	if (PagePrivate(page))
+		return 0;
+	return nfs_fscache_release_page(page, gfp);
 }
 
 /*
  * Attempt to clear the private state associated with a page when an error
  * occurs that requires the cached contents of an inode to be written back or
  * destroyed
- * - Called if either PG_private or PG_private_2 is set on the page
+ * - Called if either PG_private or fscache is set on the page
  * - Caller holds page lock
  * - Return 0 if successful, -error otherwise
  */
 static int nfs_launder_page(struct page *page)
 {
+	wait_on_page_fscache_write(page);
 	return nfs_wb_page(page->mapping->host, page);
 }
 
@@ -422,6 +428,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 	int ret = -EINVAL;
 	struct address_space *mapping;
 
+	/* make sure the cache has finished storing the page */
+	wait_on_page_fscache_write(page);
+
 	lock_page(page);
 	mapping = page->mapping;
 	if (mapping != vma->vm_file->f_path.dentry->d_inode->i_mapping)
fs/nfs/fscache.c +49 -0

58 lines not on this page · raw message

fs/nfs/fscache.h +22 -0
index d730ec8..1cb7d96 100644
@@ -86,6 +86,21 @@ extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
 extern void nfs_fscache_renew_inode_cookie(struct inode *);
 extern void nfs_fscache_attr_changed(struct inode *);
 
+extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
+extern int nfs_fscache_release_page(struct page *, gfp_t);
+
+/*
+ * release the caching state associated with a page if undergoing complete page
+ * invalidation
+ */
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode)
+{
+	if (PageFsCache(page))
+		__nfs_fscache_invalidate_page(page, inode);
+}
+
+
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
@@ -110,5 +125,12 @@ static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
 					     struct file *filp) {}
 static inline void nfs_fscache_attr_changed(struct inode *inode) {}
 
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	return 1; /* True: may release page */
+}
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode) {}
+
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */
author maintainer
#38 lore raw

PATCH 32/37 NFS: Add read context retention for FS-Cache to call back with

In reply to David Howells

Add read context retention so that FS-Cache can call back into NFS when a read operation on the cache fails EIO rather than reading data. This permits NFS to then fetch the data from the server instead using the appropriate security context.

---

 fs/nfs/fscache-index.c |   26 ++++++++++++++++++++++++++
 1 files changed, 26 insertions(+), 0 deletions(-)
fs/nfs/fscache-index.c +26 -0
index eec8e7e..af9f06b 100644
@@ -285,6 +285,30 @@ static void nfs_cache_inode_now_uncached(void *cookie_netfs_data)
 }
 
 /*
+ * Get an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ * - The read context is passed back to NFS in the event that a data read on the
+ *   cache fails with EIO - in which case the server must be contacted to
+ *   retrieve the data, which requires the read context for security.
+ */
+static void nfs_fh_get_context(void *cookie_netfs_data, void *context)
+{
+	get_nfs_open_context(context);
+}
+
+/*
+ * Release an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ */
+static void nfs_fh_put_context(void *cookie_netfs_data, void *context)
+{
+	if (context)
+		put_nfs_open_context(context);
+}
+
+/*
  * Define the inode object for FS-Cache.  This is used to describe an inode
  * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
  * an inode.
@@ -301,4 +325,6 @@ const struct fscache_cookie_def nfs_cache_inode_object_def = {
 	.get_aux	= nfs_cache_inode_get_aux,
 	.check_aux	= nfs_cache_inode_check_aux,
 	.now_uncached	= nfs_cache_inode_now_uncached,
+	.get_context	= nfs_fh_get_context,
+	.put_context	= nfs_fh_put_context,
 };
author maintainer
#39 lore raw

PATCH 33/37 NFS: nfs_readpage_async() needs to be accessible as a fallback for local caching

In reply to David Howells

nfs_readpage_async() needs to be non-static so that it can be used as a fallback for the local on-disk caching should an EIO crop up when reading the cache.

---

 fs/nfs/read.c          |    4 ++--
 include/linux/nfs_fs.h |    2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)
fs/nfs/read.c +2 -2
index 3d7d963..725a5a2 100644
@@ -114,8 +114,8 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
 	}
 }
 
-static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
-		struct page *page)
+int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
+		       struct page *page)
 {
 	LIST_HEAD(one_request);
 	struct nfs_page	*new;
include/linux/nfs_fs.h +2 -0
index d9adb53..d1d545e 100644
@@ -505,6 +505,8 @@ extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern void nfs_readdata_release(void *data);
+extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
+			       struct page *);
 
 /*
  * Allocate nfs_read_data structures
author maintainer
#40 lore raw

PATCH 34/37 NFS: Read pages from FS-Cache into an NFS inode

In reply to David Howells

Read pages from an FS-Cache data storage object representing an inode into an NFS inode.

---

 fs/nfs/fscache.c |  112 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/fscache.h |   47 +++++++++++++++++++++++
 fs/nfs/read.c    |   18 +++++++++
 3 files changed, 176 insertions(+), 1 deletions(-)
fs/nfs/fscache.c +111 -1
index d475ff5..438cc9b 100644
@@ -344,5 +344,115 @@ void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
 
 	BUG_ON(!PageLocked(page));
 	fscache_uncache_page(nfsi->fscache, page);
-	nfs_add_stats(page->mapping->host, NFSIOS_FSCACHE_UNCACHE, 1);
+	nfs_add_stats(inode, NFSIOS_FSCACHE_UNCACHE, 1);
+}
+
+/*
+ * Handle completion of a page being read from the cache.
+ * - Called in process (keventd) context.
+ */
+static void nfs_readpage_from_fscache_complete(struct page *page,
+					       void *context,
+					       int error)
+{
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
+		 page, context, error);
+
+	/* if the read completes with an error, we just unlock the page and let
+	 * the VM reissue the readpage */
+	if (!error) {
+		SetPageUptodate(page);
+		unlock_page(page);
+	} else {
+		error = nfs_readpage_async(context, page->mapping->host, page);
+		if (error)
+			unlock_page(page);
+	}
+}
+
+/*
+ * Retrieve a page from fscache
+ */
+int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+				struct inode *inode, struct page *page)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, inode);
+
+	ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
+					 page,
+					 nfs_readpage_from_fscache_complete,
+					 ctx,
+					 GFP_KERNEL);
+
+	switch (ret) {
+	case 0: /* read BIO submitted (page in fscache) */
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache: BIO submitted\n");
+		nfs_add_stats(inode, NFSIOS_FSCACHE_READ_OK, 1);
+		return ret;
+
+	case -ENOBUFS: /* inode not in cache */
+	case -ENODATA: /* page not in cache */
+		nfs_add_stats(inode, NFSIOS_FSCACHE_READ_FAIL, 1);
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
+		nfs_add_stats(inode, NFSIOS_FSCACHE_READ_FAIL, 1);
+	}
+	return ret;
+}
+
+/*
+ * Retrieve a set of pages from fscache
+ */
+int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+				 struct inode *inode,
+				 struct address_space *mapping,
+				 struct list_head *pages,
+				 unsigned *nr_pages)
+{
+	int ret, npages = *nr_pages;
+
+	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
+		 NFS_I(inode)->fscache, npages, inode);
+
+	ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
+					  mapping, pages, nr_pages,
+					  nfs_readpage_from_fscache_complete,
+					  ctx,
+					  mapping_gfp_mask(mapping));
+	if (*nr_pages < npages)
+		nfs_add_stats(inode, NFSIOS_FSCACHE_READ_OK, npages);
+	if (*nr_pages > 0)
+		nfs_add_stats(inode, NFSIOS_FSCACHE_READ_FAIL, *nr_pages);
+
+	switch (ret) {
+	case 0: /* read submitted to the cache for all pages */
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: submitted\n");
+
+		return ret;
+
+	case -ENOBUFS: /* some pages aren't cached and can't be */
+	case -ENODATA: /* some pages aren't cached */
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
+	}
+
+	return ret;
 }
fs/nfs/fscache.h +47 -0

64 lines not on this page · raw message

fs/nfs/read.c +18 -0
index 725a5a2..db27b26 100644
@@ -24,6 +24,7 @@
 
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -493,9 +494,16 @@ int nfs_readpage(struct file *file, struct page *page)
 			goto out_unlock;
 	} else
 		ctx = get_nfs_open_context(nfs_file_open_context(file));
+ 
+	if (!IS_SYNC(inode)) {
+		error = nfs_readpage_from_fscache(ctx, inode, page);
+		if (error == 0)
+			goto out;
+	}
 
 	error = nfs_readpage_async(ctx, inode, page);
 
+out:
 	put_nfs_open_context(ctx);
 	return error;
 out_unlock:
@@ -571,6 +579,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			return -EBADF;
 	} else
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
+
+	/* attempt to read as many of the pages as possible from the cache
+	 * - this returns -ENOBUFS immediately if the cookie is negative
+	 */
+	ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
+					 pages, &nr_pages);
+	if (ret == 0)
+		goto read_complete; /* all pages were read */
+
 	if (rsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
 	else
@@ -581,6 +598,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	nfs_pageio_complete(&pgio);
 	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
+read_complete:
 	put_nfs_open_context(desc.ctx);
 out:
 	return ret;

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#41 lore raw

PATCH 35/37 NFS: Store pages from an NFS inode into a local cache

In reply to David Howells

Store pages from an NFS inode into the cache data storage object associated with that inode.

---

 fs/nfs/fscache.c |   26 ++++++++++++++++++++++++++
 fs/nfs/fscache.h |   16 ++++++++++++++++
 fs/nfs/read.c    |    5 +++++
 3 files changed, 47 insertions(+), 0 deletions(-)
fs/nfs/fscache.c +26 -0
index 438cc9b..50ae70f 100644
@@ -456,3 +456,29 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 
 	return ret;
 }
+
+/*
+ * Store a newly fetched page in fscache
+ * - PG_fscache must be set on the page
+ */
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, sync);
+
+	ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
+	dfprintk(FSCACHE,
+		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
+		 page, page->index, page->flags, ret);
+
+	if (ret != 0) {
+		fscache_uncache_page(NFS_I(inode)->fscache, page);
+		nfs_add_stats(inode, NFSIOS_FSCACHE_WRITE_FAIL, 1);
+		nfs_add_stats(inode, NFSIOS_FSCACHE_UNCACHE, 1);
+	} else {
+		nfs_add_stats(inode, NFSIOS_FSCACHE_WRITE_OK, 1);
+	}
+}
fs/nfs/fscache.h +16 -0
index 4c1e1a8..6264cd8 100644
@@ -94,6 +94,7 @@ extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
 extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
 					struct inode *, struct address_space *,
 					struct list_head *, unsigned *);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
 
 /*
  * release the caching state associated with a page if undergoing complete page
@@ -133,6 +134,19 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 	return -ENOBUFS;
 }
 
+/*
+ * Store a page newly fetched from the server in an inode data storage object
+ * in the cache.
+ */
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page,
+					   int sync)
+{
+	if (PageFsCache(page))
+		__nfs_readpage_to_fscache(inode, page, sync);
+}
+
+
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
@@ -178,6 +192,8 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 {
 	return -ENOBUFS;
 }
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page, int sync) {}
 
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */
fs/nfs/read.c +5 -0
index db27b26..e09bdf9 100644
@@ -143,6 +143,11 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 
 static void nfs_readpage_release(struct nfs_page *req)
 {
+	struct inode *d_inode = req->wb_context->path.dentry->d_inode;
+
+	if (PageUptodate(req->wb_page))
+		nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
 	unlock_page(req->wb_page);
 
 	dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#42 lore raw

PATCH 36/37 NFS: Display local caching state

In reply to David Howells

Display the local caching state in /proc/fs/nfsfs/volumes.

---

 fs/nfs/client.c  |    7 ++++---
 fs/nfs/fscache.h |   15 +++++++++++++++
 2 files changed, 19 insertions(+), 3 deletions(-)
fs/nfs/client.c +4 -3
index 51e9346..d67d52f 100644
@@ -1451,7 +1451,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 
 	/* display header on line 1 */
 	if (v == &nfs_volume_list) {
-		seq_puts(m, "NV SERVER   PORT DEV     FSID\n");
+		seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
 		return 0;
 	}
 	/* display one transport per line on subsequent lines */
@@ -1465,12 +1465,13 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 		 (unsigned long long) server->fsid.major,
 		 (unsigned long long) server->fsid.minor);
 
-	seq_printf(m, "v%u %s %s %-7s %-17s\n",
+	seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
 		   dev,
-		   fsid);
+		   fsid,
+		   nfs_server_fscache_state(server));
 
 	return 0;
 }
fs/nfs/fscache.h +15 -0
index 6264cd8..5f7806f 100644
@@ -146,6 +146,16 @@ static inline void nfs_readpage_to_fscache(struct inode *inode,
 		__nfs_readpage_to_fscache(inode, page, sync);
 }
 
+/*
+ * indicate the client caching state as readable text
+ */
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+		return "yes";
+	return "no ";
+}
+
 
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
@@ -195,5 +205,10 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 static inline void nfs_readpage_to_fscache(struct inode *inode,
 					   struct page *page, int sync) {}
 
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	return "no ";
+}
+
 #endif /* CONFIG_NFS_FSCACHE */
 #endif /* _NFS_FSCACHE_H */

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.

author maintainer
#43 lore raw

PATCH 37/37 NFS: Add mount options to enable local caching on NFS

In reply to David Howells

Add NFS mount options to allow the local caching support to be enabled.

The attached patch makes it possible for the NFS filesystem to be told to make use of the network filesystem local caching service (FS-Cache).

To be able to use this, a recent nfsutils package is required.

There are three variant NFS mount options that can be added to a mount command to control caching for a mount. Only the last one specified takes effect:

(*) Adding "fsc" will request caching.

(*) Adding "fsc=<string>" will request caching and also specify a uniquifier.

(*) Adding "nofsc" will disable caching.

For example:

mount warthog:/ /a -o fsc

The cache of a particular superblock (NFS FSID) will be shared between all mounts of that volume, provided they have the same connection parameters and are not marked 'nosharecache'.

Where it is otherwise impossible to distinguish superblocks because all the parameters are identical, but the 'nosharecache' option is supplied, a uniquifying string must be supplied, else only the first mount will be permitted to use the cache.

If there's a key collision, then the second mount will disable caching and give a warning into the kernel log.

---

 fs/nfs/client.c   |    2 ++
 fs/nfs/internal.h |    1 +
 fs/nfs/super.c    |   25 +++++++++++++++++++++++++
 3 files changed, 28 insertions(+), 0 deletions(-)
fs/nfs/client.c +2 -0
index d67d52f..8357f68 100644
@@ -669,6 +669,7 @@ static int nfs_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+	server->options = data->options;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1056,6 +1057,7 @@ static int nfs4_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
 	server->caps |= NFS_CAP_ATOMIC_OPEN;
+	server->options = data->options;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
fs/nfs/internal.h +1 -0
index e49cb6e..f427b35 100644
@@ -38,6 +38,7 @@ struct nfs_parsed_mount_data {
 	int			acregmin, acregmax,
 				acdirmin, acdirmax;
 	int			namlen;
+	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
fs/nfs/super.c +25 -0
index 437c3dd..96082a2 100644
@@ -76,6 +76,7 @@ enum {
 	Opt_acl, Opt_noacl,
 	Opt_rdirplus, Opt_nordirplus,
 	Opt_sharecache, Opt_nosharecache,
+	Opt_fscache, Opt_nofscache,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -92,6 +93,7 @@ enum {
 	/* Mount options that take string arguments */
 	Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
 	Opt_addr, Opt_mountaddr, Opt_clientaddr,
+	Opt_fscache_uniq,
 
 	/* Mount options that are ignored */
 	Opt_userspace, Opt_deprecated,
@@ -125,6 +127,9 @@ static match_table_t nfs_mount_option_tokens = {
 	{ Opt_nordirplus, "nordirplus" },
 	{ Opt_sharecache, "sharecache" },
 	{ Opt_nosharecache, "nosharecache" },
+	{ Opt_fscache, "fsc" },
+	{ Opt_fscache_uniq, "fsc=%s" },
+	{ Opt_nofscache, "nofsc" },
 
 	{ Opt_port, "port=%u" },
 	{ Opt_rsize, "rsize=%u" },
@@ -482,6 +487,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	seq_printf(m, ",timeo=%lu", 10U * nfss->client->cl_timeout->to_initval / HZ);
 	seq_printf(m, ",retrans=%u", nfss->client->cl_timeout->to_retries);
 	seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor));
+	if (nfss->options & NFS_OPTION_FSCACHE)
+		seq_printf(m, ",fsc");
 }
 
 /*
@@ -776,6 +783,24 @@ static int nfs_parse_mount_options(char *raw,
 		case Opt_nosharecache:
 			mnt->flags |= NFS_MOUNT_UNSHARED;
 			break;
+		case Opt_fscache:
+			mnt->options |= NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_nofscache:
+			mnt->options &= ~NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_fscache_uniq:
+			string = match_strdup(args);
+			if (!string)
+				goto out_nomem;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = string;
+			mnt->options |= NFS_OPTION_FSCACHE;
+			break;
 
 		case Opt_port:
 			if (match_int(args, &option))

--
This message was distributed to subscribers of the selinux mailing list. If you no longer wish to subscribe, send mail to [email protected] with the words "unsubscribe selinux" without quotes as the message.