[PATCH] exporting capability code/name pairs (try #4)
This patch enables to export code/name pair of capabilities supported
on the running kernel, under the /sys/kernel/capability .
We can apply it onto the latest Linus's git tree.
Changes from the previous version:
- I added names/ ans codes/ directories, and we can use them
to lookup capability code or name non-sequentially.
In the previous version, we had to scan whole of entries to lookup
capability name by its code.
(required by Andrew Morgan)
- I added an assertion when mkcapname.sh works incorrectly.
(required by Serge E.Hallyn)
In addition, Andrew suggested me to export these translation by symlinks
to reduce the number of invocation of system call.
However, current sysfs interface does not allows to create symlinks with
invalid indication.
Thus, this patch exports them as regular files.
[EMAIL PROTECTED] ~]$ ls -R /sys/kernel/capability/
/sys/kernel/capability/:
codes names version
/sys/kernel/capability/codes:
0 10 12 14 16 18 2 21 23 25 27 29 30 32 4 6 8
1 11 13 15 17 19 20 22 24 26 28 3 31 33 5 7 9
/sys/kernel/capability/names:
cap_audit_controlcap_kill cap_net_raw cap_sys_nice
cap_audit_write cap_lease cap_setfcap cap_sys_pacct
cap_chowncap_linux_immutable cap_setgid cap_sys_ptrace
cap_dac_override cap_mac_admin cap_setpcap cap_sys_rawio
cap_dac_read_search cap_mac_override cap_setuid cap_sys_resource
cap_fowner cap_mknod cap_sys_admin cap_sys_time
cap_fsetid cap_net_admin cap_sys_bootcap_sys_tty_config
cap_ipc_lock cap_net_bind_service cap_sys_chroot
cap_ipc_ownercap_net_broadcast cap_sys_module
[EMAIL PROTECTED] ~]$ cat /sys/kernel/capability/codes/20
cap_sys_pacct
[EMAIL PROTECTED] ~]$ cat /sys/kernel/capability/names/cap_mknod
27
[EMAIL PROTECTED] ~]$
Any comment please.
Thanks,
Signed-off-by: KaiGai Kohei [EMAIL PROTECTED]
scripts/mkcapnames.sh | 44 +++
security/Kconfig |9
security/Makefile | 11 +
security/capability.c | 115 +
4 files changed, 179 insertions(+), 0 deletions(-)
diff --git a/scripts/mkcapnames.sh b/scripts/mkcapnames.sh
index e69de29..9e7290f 100644
--- a/scripts/mkcapnames.sh
+++ b/scripts/mkcapnames.sh
@@ -0,0 +1,44 @@
+#!/bin/sh
+
+#
+# generate a cap_names.h file from include/linux/capability.h
+#
+
+CAPHEAD=`dirname $0`/../include/linux/capability.h
+REGEXP='^#define CAP_[A-Z_]+[ ]+[0-9]+$'
+NUMCAP=`cat $CAPHEAD | egrep -c $REGEXP`
+
+echo '#ifndef CAP_NAMES_H'
+echo '#define CAP_NAMES_H'
+echo
+echo '/*'
+echo ' * Do NOT edit this file directly.'
+echo ' * This file is generated from include/linux/capability.h automatically'
+echo ' */'
+echo
+echo '#if !defined(SYSFS_CAP_NAME_ENTRY) || !defined(SYSFS_CAP_CODE_ENTRY)'
+echo '#error cap_names.h should be included from security/capability.c'
+echo '#else'
+echo #if $NUMCAP != CAP_LAST_CAP + 1
+echo '#error mkcapnames.sh cannot collect capabilities correctly'
+echo '#else'
+cat $CAPHEAD | egrep $REGEXP \
+| awk '{ printf(SYSFS_CAP_NAME_ENTRY(%s,%s);\n, tolower($2), $2); }'
+echo
+echo 'static struct attribute *capability_name_attrs[] = {'
+cat $CAPHEAD | egrep $REGEXP \
+| awk '{ printf(\t%s_name_attr.attr,\n, tolower($2)); } END { print
\tNULL, }'
+echo '};'
+
+echo
+cat $CAPHEAD | egrep $REGEXP \
+| awk '{ printf(SYSFS_CAP_CODE_ENTRY(%s,%s);\n, tolower($2), $2); }'
+echo
+echo 'static struct attribute *capability_code_attrs[] = {'
+cat $CAPHEAD | egrep $REGEXP \
+| awk '{ printf(\t%s_code_attr.attr,\n, tolower($2)); } END { print
\tNULL, }'
+echo '};'
+
+echo '#endif'
+echo '#endif'
+echo '#endif'
diff --git a/security/Kconfig b/security/Kconfig
index 25ffe1b..b79e830 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -91,6 +91,15 @@ config SECURITY_FILE_CAPABILITIES
If in doubt, answer N.
+config SECURITY_CAPABILITIES_EXPORT
+ bool Exporting capabilities kernel supported
+ depends on SECURITY_CAPABILITIES SYSFS
+ help
+ This enables to export any capabilities which are supported
+ in the running kernel.
+
+ If you are unsure how to answer this question, answer Y.
+
config SECURITY_ROOTPLUG
bool Root Plug Support
depends on USB=y SECURITY
diff --git a/security/Makefile b/security/Makefile
index 9e8b025..0e80903 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -18,3 +18,14 @@ obj-$(CONFIG_SECURITY_SELINUX) +=
selinux/built-in.o
obj-$(CONFIG_SECURITY_SMACK) += commoncap.o smack/built-in.o
obj-$(CONFIG_SECURITY_CAPABILITIES)+= commoncap.o capability.o
obj-$(CONFIG_SECURITY_ROOTPLUG)+= commoncap.o root_plug.o
+
+ifeq
[PATCH 34/37] NFS: Read pages from FS-Cache into an NFS inode
Read pages from an FS-Cache data storage object representing an inode into an
NFS inode.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/fscache.c | 112 ++
fs/nfs/fscache.h | 47 +++
fs/nfs/read.c| 18 +
3 files changed, 176 insertions(+), 1 deletions(-)
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index d475ff5..438cc9b 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -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;
}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 1cb7d96..4c1e1a8 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -89,6 +89,12
[PATCH 35/37] NFS: Store pages from an NFS inode into a local cache
Store pages from an NFS inode into the cache data storage object associated
with that inode.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/fscache.c | 26 ++
fs/nfs/fscache.h | 16
fs/nfs/read.c|5 +
3 files changed, 47 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 438cc9b..50ae70f 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -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);
+ }
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 4c1e1a8..6264cd8 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -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 */
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index db27b26..e09bdf9 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -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 [EMAIL PROTECTED])\n,
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 23/37] NFS: Permit local filesystem caching to be enabled for NFS
Permit local filesystem caching to be enabled for NFS in the kernel configuration. Signed-off-by: David Howells [EMAIL PROTECTED] --- fs/Kconfig |8 1 files changed, 8 insertions(+), 0 deletions(-) diff --git a/fs/Kconfig b/fs/Kconfig index c42ec50..fa8e978 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -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 - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 29/37] NFS: Invalidate FsCache page flags when cache removed
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/fscache-index.c | 40
1 files changed, 40 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index c3c63fa..eec8e7e 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -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,
};
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 26/37] NFS: Define and create superblock-level objects
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
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(-)
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 25ac4a1..b5a52e3 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -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,
+};
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index dcc1800..cbd09f0 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -23,6 +23,9 @@
#define NFSDBG_FACILITYNFSDBG_FSCACHE
+static struct rb_root nfs_fscache_keys = RB_ROOT;
+static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
+
/*
* Get the per-client index cookie for an NFS client if the appropriate mount
* flag was set
@@ -50,3 +53,116 @@ void nfs_fscache_release_client_cookie(struct nfs_client
*clp)
fscache_relinquish_cookie(clp-fscache, 0);
clp-fscache = NULL;
}
+
+/*
+ * Get the cache cookie for an NFS superblock. We have to handle
+ * uniquification here because the cache doesn't do it for us.
+ */
+void nfs_fscache_get_super_cookie(struct super_block *sb,
+ struct nfs_parsed_mount_data *data)
+{
+ struct nfs_fscache_key *key, *xkey;
+ struct nfs_server *nfss = NFS_SB(sb);
+ struct rb_node **p, *parent;
+ const char *uniq = data-fscache_uniq ?: ;
+ int diff, ulen;
+
+ ulen = strlen(uniq);
+ key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
+ if (!key)
+ return;
+
+ key-nfs_client = nfss-nfs_client;
+ key-key.super.s_flags = sb-s_flags NFS_MS_MASK;
+ key-key.nfs_server.flags = nfss-flags;
+ key-key.nfs_server.rsize = nfss-rsize;
+ key-key.nfs_server.wsize = nfss-wsize;
+ key-key.nfs_server.acregmin = nfss-acregmin;
+ key-key.nfs_server.acregmax = nfss-acregmax;
+ key-key.nfs_server.acdirmin = nfss-acdirmin;
+ key-key.nfs_server.acdirmax = nfss-acdirmax;
+ key-key.nfs_server.fsid = nfss-fsid;
+ key-key.rpc_auth.au_flavor = nfss-client-cl_auth-au_flavor;
+
+ key-key.uniq_len = ulen;
+
[PATCH 24/37] NFS: Register NFS for caching and retrieve the top-level index
Register NFS for caching and retrieve the top-level cache index object cookie.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
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
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index df0f41e..6d7176d 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -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
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
new file mode 100644
index 000..225ed5d
--- /dev/null
+++ b/fs/nfs/fscache-index.c
@@ -0,0 +1,53 @@
+/* NFS FS-Cache index structure definition
+ *
+ * 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.
+ */
+
+#include linux/init.h
+#include linux/kernel.h
+#include linux/sched.h
+#include linux/mm.h
+#include linux/nfs_fs.h
+#include linux/nfs_fs_sb.h
+#include linux/in6.h
+
+#include internal.h
+#include fscache.h
+
+#define NFSDBG_FACILITYNFSDBG_FSCACHE
+
+static const struct fscache_netfs_operations nfs_cache_ops = {
+};
+
+/*
+ * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks
+ * the cookie for the top-level index object for NFS into this structure. The
+ * top-level index can than have other cache objects inserted into it.
+ */
+struct fscache_netfs nfs_cache_netfs = {
+ .name = nfs,
+ .version= 0,
+ .ops= nfs_cache_ops,
+};
+
+/*
+ * Register NFS for caching
+ */
+int nfs_fscache_register(void)
+{
+ return fscache_register_netfs(nfs_cache_netfs);
+}
+
+/*
+ * Unregister NFS for caching
+ */
+void nfs_fscache_unregister(void)
+{
+ fscache_unregister_netfs(nfs_cache_netfs);
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
new file mode 100644
index 000..75e5a03
--- /dev/null
+++ b/fs/nfs/fscache.h
@@ -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 */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 966a885..7254d5c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -46,6 +46,7 @@
#include delegation.h
#include iostat.h
#include internal.h
+#include fscache.h
#define NFSDBG_FACILITYNFSDBG_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
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 25/37] NFS: Define and create server-level objects
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
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
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 6d7176d..d848c97 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -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
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index c5c0175..51e9346 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -45,6 +45,7 @@
#include delegation.h
#include iostat.h
#include internal.h
+#include fscache.h
#define NFSDBG_FACILITYNFSDBG_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);
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 225ed5d..25ac4a1 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -51,3 +51,68 @@ void nfs_fscache_unregister(void)
{
fscache_unregister_netfs(nfs_cache_netfs);
}
+
+/*
+ * Layout of the key for an NFS server cache object.
+ */
+struct nfs_server_key {
+ uint16_tnfsversion; /* NFS protocol version */
+ uint16_tfamily; /* address family */
+ uint16_tport; /* IP port */
+ union {
+ struct in_addr ipv4_addr; /* IPv4 address */
+ struct in6_addr ipv6_addr; /* IPv6 address */
+ } addr[0];
+};
+
+/*
+ * Generate a key to describe a server in the main NFS index
+ * - We return the length of the key, or 0 if we can't generate one
+ */
+static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
+ void *buffer, uint16_t bufmax)
+{
+ const struct nfs_client *clp = cookie_netfs_data;
+ const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) clp-cl_addr;
+ const struct sockaddr_in *sin = (struct sockaddr_in *) clp-cl_addr;
+ struct nfs_server_key *key = buffer;
+ uint16_t len = 0;
+
+ key-nfsversion = clp-rpc_ops-version;
+ key-family = clp-cl_addr.ss_family;
+
+ len = sizeof(struct nfs_server_key);
+
+ switch (clp-cl_addr.ss_family) {
+ case AF_INET:
+ key-port = sin-sin_port;
+ key-addr[0].ipv4_addr = sin-sin_addr;
+ len += sizeof(key-addr[0].ipv4_addr);
+ break;
+
+ case AF_INET6:
+ key-port = sin6-sin6_port;
+ key-addr[0].ipv6_addr = sin6-sin6_addr;
+ len += sizeof(key-addr[0].ipv6_addr);
+ break;
+
+ default:
+ printk(KERN_WARNING NFS: Unknown network family '%d'\n,
+ clp-cl_addr.ss_family);
+ len = 0;
+ break;
+ }
+
+ return len;
+}
+
+/*
+ * Define the server object for FS-Cache. This is used to describe a server
+ * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and
+ * server address parameters.
+ */
+const struct fscache_cookie_def nfs_cache_server_index_def = {
+ .name = NFS.server,
+ .type = FSCACHE_COOKIE_TYPE_INDEX,
+ .get_key= nfs_server_get_key,
+};
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
new file mode 100644
index
[PATCH 15/37] CacheFiles: Add missing copy_page export for ia64
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. Signed-off-by: Prarit Bhargava [EMAIL PROTECTED] Signed-off-by: David Howells [EMAIL PROTECTED] --- arch/ia64/kernel/ia64_ksyms.c |1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 8e7193d..3e544f4 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -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); - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 22/37] NFS: Add FS-Cache option bit and debug bit
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
include/linux/nfs_fs.h|1 +
include/linux/nfs_fs_sb.h |2 ++
2 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index a69ba80..14894c9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -578,6 +578,7 @@ extern void * nfs_root_data(void);
#define NFSDBG_CALLBACK0x0100
#define NFSDBG_CLIENT 0x0200
#define NFSDBG_MOUNT 0x0400
+#define NFSDBG_FSCACHE 0x0800
#define NFSDBG_ALL 0x
#ifdef __KERNEL__
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 3423c67..e7c4cdd 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -99,6 +99,8 @@ struct nfs_server {
unsigned intacdirmin;
unsigned intacdirmax;
unsigned intnamelen;
+ unsigned intoptions;/* extra options enabled by
mount */
+#define NFS_OPTION_FSCACHE 0x0001 /* - local caching enabled */
struct nfs_fsid fsid;
__u64 maxfilesize;/* maximum file size */
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 19/37] CacheFiles: Export things for CacheFiles
Export a number of functions for CacheFiles's use. Signed-off-by: David Howells [EMAIL PROTECTED] --- fs/super.c |1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/fs/super.c b/fs/super.c index ceaf2e3..cd199ae 100644 --- a/fs/super.c +++ b/fs/super.c @@ -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() - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 16/37] CacheFiles: Be consistent about the use of mapping vs file-f_mapping in Ext3
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/ext3/inode.c |6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index eb95670..c976123 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -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;
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 12/37] FS-Cache: Recruit a couple of page flags for cache management
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. Signed-off-by: David Howells [EMAIL PROTECTED] --- 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(-) diff --git a/fs/splice.c b/fs/splice.c index 4ee49e8..01b8c43 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -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); /* diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index bbad43f..cc16c23 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -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_reserved10 #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_compound14 /* Part of a compound page */ #define PG_swapcache 15 /* Swap page: swp_entry_t in private */ #define PG_mappedtodisk16 /* Has blocks allocated on-disk */ #define PG_reclaim 17 /* To be reclaimed asap */ +#define PG_owner_priv_218 /* 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)
[PATCH 11/37] FS-Cache: Release page-private after failed readahead
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
mm/readahead.c | 39 +--
1 files changed, 37 insertions(+), 2 deletions(-)
diff --git a/mm/readahead.c b/mm/readahead.c
index c9c50ca..75aa6b6 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -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);
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 10/37] Security: Make NFSD work with detached security
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfsd/auth.c| 37 +++-
fs/nfsd/nfs4recover.c | 64 +++--
2 files changed, 65 insertions(+), 36 deletions(-)
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 5586157..ebdc562 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -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;
}
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index bf0217a..ae91262 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -46,27 +46,37 @@
#include linux/scatterlist.h
#include linux/crypto.h
#include linux/sched.h
+#include linux/cred.h
#define NFSDDBG_FACILITYNFSDDBG_PROC
/* Globals */
static struct nameidata rec_dir;
static int rec_dir_init = 0;
+static struct task_security *rec_security;
+/*
+ * switch the special recovery access security in on the current task's
+ * subjective security
+ */
static void
-nfs4_save_user(uid_t *saveuid, gid_t *savegid)
+nfs4_begin_secure(struct task_security **saved_sec)
{
- *saveuid = current-act_as-fsuid;
- *savegid = current-act_as-fsgid;
- current-act_as-fsuid = 0;
- current-act_as-fsgid = 0;
+ *saved_sec = current-act_as;
+ current-act_as = get_task_security(rec_security);
}
+/*
+ * return the current task's subjective security to its former glory
+ */
static void
-nfs4_reset_user(uid_t saveuid, gid_t
[PATCH 00/37] 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 - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 36/37] NFS: Display local caching state
Display the local caching state in /proc/fs/nfsfs/volumes.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/client.c |7 ---
fs/nfs/fscache.h | 15 +++
2 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 51e9346..d67d52f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -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;
}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 6264cd8..5f7806f 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -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 */
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 30/37] NFS: Add some new I/O event counters for FS-Cache events
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/iostat.h |7 +++
1 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index 6350ecb..0e3b170 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -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,
};
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 28/37] NFS: Use local disk inode cache
Bind data storage objects in the local cache to NFS inodes.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
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(-)
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index cbd09f0..c0e0320 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -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);
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 7dcdf32..d730ec8 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -77,6 +77,15 @@ extern void nfs_fscache_get_super_cookie(struct super_block
*,
struct nfs_parsed_mount_data *);
extern void
[PATCH 27/37] NFS: Define and create inode-level cache objects
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/fscache-index.c | 112
fs/nfs/fscache.h |1
2 files changed, 113 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index b5a52e3..c3c63fa 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -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
[PATCH 21/37] NFS: Add comment banners to some NFS functions
Add comment banners to some NFS functions so that they can be modified by the
NFS fscache patches for further information.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/file.c | 26 ++
1 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index ef57a5a..26a073b 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -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;
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 17/37] CacheFiles: Add a hook to write a single page of data to an inode
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
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(-)
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index c620068..f483014 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -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,
};
/*
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index c976123..0209f3b 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -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)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index feea65d..35525c4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -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,
diff --git a/mm/filemap.c b/mm/filemap.c
index 89f5a5e..6c6cd76 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2367,6 +2367,67 @@ generic_file_buffered_write(struct kiocb *iocb, const
struct iovec *iov,
}
EXPORT_SYMBOL(generic_file_buffered_write);
+/**
+ * generic_file_buffered_write_one_page - Write a single page of data to an
+ * inode
+ * @mapping - The address space of the target inode
+ * @index - The target page in the target inode to fill
+ * @source - The data to write into the target page
+ *
+ * Write the data from the source page to the page in the nominated address
+ * space at the @index specified. Note that the file will not be extended if
+ * the page crosses the EOF marker, in which case only the first part of the
+ * page will be written.
+ *
+ * The @source page does not need to have any association with
[PATCH 04/37] KEYS: Add keyctl function to get a security label
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
Acked-by: Stephen Smalley [EMAIL PROTECTED]
---
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(-)
diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index b82d38d..be424b0 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -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
===
diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h
index 3365945..656ee6b 100644
--- a/include/linux/keyctl.h
+++ b/include/linux/keyctl.h
@@ -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_AUTHORITY16 /* assume request_key()
authorisation */
+#define KEYCTL_GET_SECURITY17 /* get key security label */
#endif /* _LINUX_KEYCTL_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index fe52cde..a33fd03 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -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
Re: [PATCH] exporting capability code/name pairs (try #4)
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 KaiGai, Thanks for trying to accommodate me :-) Kohei KaiGai wrote: | In addition, Andrew suggested me to export these translation by symlinks | to reduce the number of invocation of system call. Yes, I wanted to make use of readlink() instead of open()/read()/close() to access each unknown capability. | However, current sysfs interface does not allows to create symlinks with | invalid indication. :-( | Thus, this patch exports them as regular files. What about using symlinks for the name files and text content for the numeric ones? You could even drop the names/ and codes/ subdirectories too: $ cat /sys/kernel/capability/20 cap_sys_pacct $ ls -l /sys/kernel/capability/cap_mknod lr--r--r-- 1 root root 64 Feb 8 08:26 cap_mknod - 27 $ cat /sys/kernel/capability/names/cap_mknod cap_mknod Cheers Andrew -BEGIN PGP SIGNATURE- Version: GnuPG v1.2.6 (GNU/Linux) iD8DBQFHrIfh+bHCR3gb8jsRAkueAKDYMu+so+YCJD9klNentiWlwZJXlQCgrzSa tWr1XM1nKcvST1ScAfO27j4= =w5N/ -END PGP SIGNATURE- - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 31/37] NFS: FS-Cache page management
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).
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/file.c| 17 +
fs/nfs/fscache.c | 49 +
fs/nfs/fscache.h | 22 ++
3 files changed, 84 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 26a073b..60db3ea 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -35,6 +35,7 @@
#include delegation.h
#include internal.h
#include iostat.h
+#include fscache.h
#define NFSDBG_FACILITYNFSDBG_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)
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index c0e0320..d475ff5 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -19,6 +19,7 @@
#include linux/seq_file.h
#include internal.h
+#include iostat.h
#include fscache.h
#define NFSDBG_FACILITYNFSDBG_FSCACHE
@@ -297,3 +298,51 @@ void nfs_fscache_attr_changed(struct inode *inode)
{
fscache_attr_changed(NFS_I(inode)-fscache);
}
+
+/*
+ * Release the caching state associated with a page, if the page isn't busy
+ * interacting with the cache.
+ * - Returns true (can release page) or false (page busy).
+ */
+int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ if (PageFsCacheWrite(page)) {
+ if (!(gfp __GFP_WAIT))
+ return 0;
+ wait_on_page_fscache_write(page);
+ }
+
+ if (PageFsCache(page)) {
+ struct nfs_inode *nfsi = NFS_I(page-mapping-host);
+
+ BUG_ON(!nfsi-fscache);
+
+ dfprintk(FSCACHE, NFS: fscache releasepage (0x%p/0x%p/0x%p)\n,
+nfsi-fscache, page, nfsi);
+
+ fscache_uncache_page(nfsi-fscache, page);
+ nfs_add_stats(page-mapping-host, NFSIOS_FSCACHE_UNCACHE, 1);
+ }
+
+ return 1;
+}
+
+/*
+ * Release the caching state associated with a page if undergoing complete page
+ * invalidation.
+ */
+void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ BUG_ON(!nfsi-fscache);
+
+ dfprintk(FSCACHE, NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n,
+nfsi-fscache, page, nfsi);
+
+ wait_on_page_fscache_write(page);
+
+ BUG_ON(!PageLocked(page));
+ fscache_uncache_page(nfsi-fscache, page);
+ nfs_add_stats(page-mapping-host, NFSIOS_FSCACHE_UNCACHE, 1);
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index d730ec8..1cb7d96
Re: [PATCH] exporting capability code/name pairs (try #4)
On Fri, Feb 08, 2008 at 06:42:09PM +0900, Kohei KaiGai wrote: [EMAIL PROTECTED] ~]$ ls -R /sys/kernel/capability/ /sys/kernel/capability/: codes names version /sys/kernel/capability/codes: 0 10 12 14 16 18 2 21 23 25 27 29 30 32 4 6 8 1 11 13 15 17 19 20 22 24 26 28 3 31 33 5 7 9 /sys/kernel/capability/names: cap_audit_controlcap_kill cap_net_raw cap_sys_nice cap_audit_write cap_lease cap_setfcap cap_sys_pacct cap_chowncap_linux_immutable cap_setgid cap_sys_ptrace cap_dac_override cap_mac_admin cap_setpcap cap_sys_rawio cap_dac_read_search cap_mac_override cap_setuid cap_sys_resource cap_fowner cap_mknod cap_sys_admin cap_sys_time cap_fsetid cap_net_admin cap_sys_bootcap_sys_tty_config cap_ipc_lock cap_net_bind_service cap_sys_chroot cap_ipc_ownercap_net_broadcast cap_sys_module [EMAIL PROTECTED] ~]$ cat /sys/kernel/capability/codes/20 cap_sys_pacct [EMAIL PROTECTED] ~]$ cat /sys/kernel/capability/names/cap_mknod 27 [EMAIL PROTECTED] ~]$ Any comment please. You don't like 1 (one) /proc/capabilities, why? - To unsubscribe from this list: send the line unsubscribe linux-security-module in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 33/37] NFS: nfs_readpage_async() needs to be accessible as a fallback for local caching
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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
fs/nfs/read.c |4 ++--
include/linux/nfs_fs.h |2 ++
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 3d7d963..725a5a2 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -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;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index d9adb53..d1d545e 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -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
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 05/37] Security: Change current-fs[ug]id to current_fs[ug]id()
Change current-fs[ug]id to current_fs[ug]id() so that fsgid and fsuid can be separated from the task_struct. Signed-off-by: David Howells [EMAIL PROTECTED] --- 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(-) diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 78acd9f..9ef832c 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -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; diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 90784c0..0c3838c 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -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 =
[PATCH 01/37] 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.
Signed-off-by: David Howells [EMAIL PROTECTED]
---
security/keys/keyctl.c | 38 ++
1 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index d9ca15c..8ec8432 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -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;
-
To unsubscribe from this list: send the line unsubscribe
linux-security-module in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
