summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/Kconfig13
-rw-r--r--fs/9p/Makefile4
-rw-r--r--fs/9p/vfs_inode.c2
-rw-r--r--fs/9p/xattr.c4
-rw-r--r--fs/9p/xattr.h2
-rw-r--r--fs/9p/xattr_security.c80
-rw-r--r--fs/9p/xattr_trusted.c80
-rw-r--r--fs/binfmt_aout.c2
-rw-r--r--fs/binfmt_elf.c2
-rw-r--r--fs/ecryptfs/crypto.c337
-rw-r--r--fs/ecryptfs/file.c7
-rw-r--r--fs/ecryptfs/main.c7
-rw-r--r--fs/ecryptfs/messaging.c3
-rw-r--r--fs/jfs/jfs_dmap.c70
-rw-r--r--fs/jfs/jfs_dtree.c37
-rw-r--r--fs/jfs/jfs_extent.c2
-rw-r--r--fs/jfs/jfs_imap.c69
-rw-r--r--fs/jfs/jfs_metapage.c5
-rw-r--r--fs/jfs/jfs_superblock.h1
-rw-r--r--fs/jfs/jfs_txnmgr.c2
-rw-r--r--fs/jfs/jfs_xtree.c62
-rw-r--r--fs/jfs/namei.c2
-rw-r--r--fs/jfs/resize.c2
-rw-r--r--fs/jfs/super.c22
-rw-r--r--fs/jfs/xattr.c8
-rw-r--r--fs/nfsd/Kconfig16
-rw-r--r--fs/nfsd/nfs4proc.c44
-rw-r--r--fs/nfsd/nfs4state.c225
-rw-r--r--fs/nfsd/nfs4xdr.c169
-rw-r--r--fs/nfsd/nfsd.h20
-rw-r--r--fs/nfsd/nfssvc.c2
-rw-r--r--fs/nfsd/state.h1
-rw-r--r--fs/nfsd/vfs.c28
-rw-r--r--fs/nfsd/vfs.h7
-rw-r--r--fs/nfsd/xdr4.h4
-rw-r--r--fs/select.c62
36 files changed, 865 insertions, 538 deletions
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig
index 55abfd6..6489e1f 100644
--- a/fs/9p/Kconfig
+++ b/fs/9p/Kconfig
@@ -31,3 +31,16 @@ config 9P_FS_POSIX_ACL
If you don't know what Access Control Lists are, say N
endif
+
+
+config 9P_FS_SECURITY
+ bool "9P Security Labels"
+ depends on 9P_FS
+ help
+ Security labels support alternative access control models
+ implemented by security modules like SELinux. This option
+ enables an extended attribute handler for file security
+ labels in the 9P filesystem.
+
+ If you are not using a security module that requires using
+ extended attributes for file security labels, say N.
diff --git a/fs/9p/Makefile b/fs/9p/Makefile
index ab8c127..ff7be98 100644
--- a/fs/9p/Makefile
+++ b/fs/9p/Makefile
@@ -11,7 +11,9 @@ obj-$(CONFIG_9P_FS) := 9p.o
v9fs.o \
fid.o \
xattr.o \
- xattr_user.o
+ xattr_user.o \
+ xattr_trusted.o
9p-$(CONFIG_9P_FSCACHE) += cache.o
9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o
+9p-$(CONFIG_9P_FS_SECURITY) += xattr_security.o
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index d86edc8..25b018e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1054,13 +1054,11 @@ static int
v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
- int err;
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
struct p9_wstat *st;
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
- err = -EPERM;
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
generic_fillattr(dentry->d_inode, stat);
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index c45e016..3c28cdf 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -167,9 +167,13 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
const struct xattr_handler *v9fs_xattr_handlers[] = {
&v9fs_xattr_user_handler,
+ &v9fs_xattr_trusted_handler,
#ifdef CONFIG_9P_FS_POSIX_ACL
&v9fs_xattr_acl_access_handler,
&v9fs_xattr_acl_default_handler,
#endif
+#ifdef CONFIG_9P_FS_SECURITY
+ &v9fs_xattr_security_handler,
+#endif
NULL
};
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
index eec348a..d3e2ea3 100644
--- a/fs/9p/xattr.h
+++ b/fs/9p/xattr.h
@@ -20,6 +20,8 @@
extern const struct xattr_handler *v9fs_xattr_handlers[];
extern struct xattr_handler v9fs_xattr_user_handler;
+extern struct xattr_handler v9fs_xattr_trusted_handler;
+extern struct xattr_handler v9fs_xattr_security_handler;
extern const struct xattr_handler v9fs_xattr_acl_access_handler;
extern const struct xattr_handler v9fs_xattr_acl_default_handler;
diff --git a/fs/9p/xattr_security.c b/fs/9p/xattr_security.c
new file mode 100644
index 0000000..cb247a1
--- /dev/null
+++ b/fs/9p/xattr_security.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include "xattr.h"
+
+static int v9fs_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ int retval;
+ char *full_name;
+ size_t name_len;
+ size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
+
+ if (name == NULL)
+ return -EINVAL;
+
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+
+ name_len = strlen(name);
+ full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+ if (!full_name)
+ return -ENOMEM;
+ memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len);
+ memcpy(full_name+prefix_len, name, name_len);
+ full_name[prefix_len + name_len] = '\0';
+
+ retval = v9fs_xattr_get(dentry, full_name, buffer, size);
+ kfree(full_name);
+ return retval;
+}
+
+static int v9fs_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
+{
+ int retval;
+ char *full_name;
+ size_t name_len;
+ size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
+
+ if (name == NULL)
+ return -EINVAL;
+
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+
+ name_len = strlen(name);
+ full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+ if (!full_name)
+ return -ENOMEM;
+ memcpy(full_name, XATTR_SECURITY_PREFIX, prefix_len);
+ memcpy(full_name + prefix_len, name, name_len);
+ full_name[prefix_len + name_len] = '\0';
+
+ retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
+ kfree(full_name);
+ return retval;
+}
+
+struct xattr_handler v9fs_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = v9fs_xattr_security_get,
+ .set = v9fs_xattr_security_set,
+};
diff --git a/fs/9p/xattr_trusted.c b/fs/9p/xattr_trusted.c
new file mode 100644
index 0000000..e30d33b
--- /dev/null
+++ b/fs/9p/xattr_trusted.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include "xattr.h"
+
+static int v9fs_xattr_trusted_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ int retval;
+ char *full_name;
+ size_t name_len;
+ size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+
+ if (name == NULL)
+ return -EINVAL;
+
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+
+ name_len = strlen(name);
+ full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+ if (!full_name)
+ return -ENOMEM;
+ memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len);
+ memcpy(full_name+prefix_len, name, name_len);
+ full_name[prefix_len + name_len] = '\0';
+
+ retval = v9fs_xattr_get(dentry, full_name, buffer, size);
+ kfree(full_name);
+ return retval;
+}
+
+static int v9fs_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
+{
+ int retval;
+ char *full_name;
+ size_t name_len;
+ size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+
+ if (name == NULL)
+ return -EINVAL;
+
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+
+ name_len = strlen(name);
+ full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+ if (!full_name)
+ return -ENOMEM;
+ memcpy(full_name, XATTR_TRUSTED_PREFIX, prefix_len);
+ memcpy(full_name + prefix_len, name, name_len);
+ full_name[prefix_len + name_len] = '\0';
+
+ retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
+ kfree(full_name);
+ return retval;
+}
+
+struct xattr_handler v9fs_xattr_trusted_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .get = v9fs_xattr_trusted_get,
+ .set = v9fs_xattr_trusted_set,
+};
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index bce8769..89dec7f 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -255,8 +255,6 @@ static int load_aout_binary(struct linux_binprm * bprm)
(current->mm->start_data = N_DATADDR(ex));
current->mm->brk = ex.a_bss +
(current->mm->start_brk = N_BSSADDR(ex));
- current->mm->free_area_cache = current->mm->mmap_base;
- current->mm->cached_hole_size = 0;
retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
if (retval < 0) {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f8a0b0e..100edcc 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -738,8 +738,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
- current->mm->free_area_cache = current->mm->mmap_base;
- current->mm->cached_hole_size = 0;
retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
executable_stack);
if (retval < 0) {
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index cfa109a..d107576 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -37,16 +37,8 @@
#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
-static int
-ecryptfs_decrypt_page_offset(struct ecryptfs_crypt_stat *crypt_stat,
- struct page *dst_page, int dst_offset,
- struct page *src_page, int src_offset, int size,
- unsigned char *iv);
-static int
-ecryptfs_encrypt_page_offset(struct ecryptfs_crypt_stat *crypt_stat,
- struct page *dst_page, int dst_offset,
- struct page *src_page, int src_offset, int size,
- unsigned char *iv);
+#define DECRYPT 0
+#define ENCRYPT 1
/**
* ecryptfs_to_hex
@@ -336,19 +328,20 @@ static void extent_crypt_complete(struct crypto_async_request *req, int rc)
}
/**
- * encrypt_scatterlist
+ * crypt_scatterlist
* @crypt_stat: Pointer to the crypt_stat struct to initialize.
- * @dest_sg: Destination of encrypted data
- * @src_sg: Data to be encrypted
- * @size: Length of data to be encrypted
- * @iv: iv to use during encryption
+ * @dst_sg: Destination of the data after performing the crypto operation
+ * @src_sg: Data to be encrypted or decrypted
+ * @size: Length of data
+ * @iv: IV to use
+ * @op: ENCRYPT or DECRYPT to indicate the desired operation
*
- * Returns the number of bytes encrypted; negative value on error
+ * Returns the number of bytes encrypted or decrypted; negative value on error
*/
-static int encrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
- struct scatterlist *dest_sg,
- struct scatterlist *src_sg, int size,
- unsigned char *iv)
+static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
+ struct scatterlist *dst_sg,
+ struct scatterlist *src_sg, int size,
+ unsigned char *iv, int op)
{
struct ablkcipher_request *req = NULL;
struct extent_crypt_result ecr;
@@ -391,9 +384,9 @@ static int encrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
crypt_stat->flags |= ECRYPTFS_KEY_SET;
}
mutex_unlock(&crypt_stat->cs_tfm_mutex);
- ecryptfs_printk(KERN_DEBUG, "Encrypting [%d] bytes.\n", size);
- ablkcipher_request_set_crypt(req, src_sg, dest_sg, size, iv);
- rc = crypto_ablkcipher_encrypt(req);
+ ablkcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
+ rc = op == ENCRYPT ? crypto_ablkcipher_encrypt(req) :
+ crypto_ablkcipher_decrypt(req);
if (rc == -EINPROGRESS || rc == -EBUSY) {
struct extent_crypt_result *ecr = req->base.data;
@@ -407,41 +400,43 @@ out:
}
/**
- * ecryptfs_lower_offset_for_extent
+ * lower_offset_for_page
*
* Convert an eCryptfs page index into a lower byte offset
*/
-static void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num,
- struct ecryptfs_crypt_stat *crypt_stat)
+static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
+ struct page *page)
{
- (*offset) = ecryptfs_lower_header_size(crypt_stat)
- + (crypt_stat->extent_size * extent_num);
+ return ecryptfs_lower_header_size(crypt_stat) +
+ (page->index << PAGE_CACHE_SHIFT);
}
/**
- * ecryptfs_encrypt_extent
- * @enc_extent_page: Allocated page into which to encrypt the data in
- * @page
+ * crypt_extent
* @crypt_stat: crypt_stat containing cryptographic context for the
* encryption operation
- * @page: Page containing plaintext data extent to encrypt
+ * @dst_page: The page to write the result into
+ * @src_page: The page to read from
* @extent_offset: Page extent offset for use in generating IV
+ * @op: ENCRYPT or DECRYPT to indicate the desired operation
*
- * Encrypts one extent of data.
+ * Encrypts or decrypts one extent of data.
*
* Return zero on success; non-zero otherwise
*/
-static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
- struct ecryptfs_crypt_stat *crypt_stat,
- struct page *page,
- unsigned long extent_offset)
+static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat,
+ struct page *dst_page,
+ struct page *src_page,
+ unsigned long extent_offset, int op)
{
+ pgoff_t page_index = op == ENCRYPT ? src_page->index : dst_page->index;
loff_t extent_base;
char extent_iv[ECRYPTFS_MAX_IV_BYTES];
+ struct scatterlist src_sg, dst_sg;
+ size_t extent_size = crypt_stat->extent_size;
int rc;
- extent_base = (((loff_t)page->index)
- * (PAGE_CACHE_SIZE / crypt_stat->extent_size));
+ extent_base = (((loff_t)page_index) * (PAGE_CACHE_SIZE / extent_size));
rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
(extent_base + extent_offset));
if (rc) {
@@ -450,15 +445,21 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
(unsigned long long)(extent_base + extent_offset), rc);
goto out;
}
- rc = ecryptfs_encrypt_page_offset(crypt_stat, enc_extent_page, 0,
- page, (extent_offset
- * crypt_stat->extent_size),
- crypt_stat->extent_size, extent_iv);
+
+ sg_init_table(&src_sg, 1);
+ sg_init_table(&dst_sg, 1);
+
+ sg_set_page(&src_sg, src_page, extent_size,
+ extent_offset * extent_size);
+ sg_set_page(&dst_sg, dst_page, extent_size,
+ extent_offset * extent_size);
+
+ rc = crypt_scatterlist(crypt_stat, &dst_sg, &src_sg, extent_size,
+ extent_iv, op);
if (rc < 0) {
- printk(KERN_ERR "%s: Error attempting to encrypt page with "
- "page->index = [%ld], extent_offset = [%ld]; "
- "rc = [%d]\n", __func__, page->index, extent_offset,
- rc);
+ printk(KERN_ERR "%s: Error attempting to crypt page with "
+ "page_index = [%ld], extent_offset = [%ld]; "
+ "rc = [%d]\n", __func__, page_index, extent_offset, rc);
goto out;
}
rc = 0;
@@ -489,6 +490,7 @@ int ecryptfs_encrypt_page(struct page *page)
char *enc_extent_virt;
struct page *enc_extent_page = NULL;
loff_t extent_offset;
+ loff_t lower_offset;
int rc = 0;
ecryptfs_inode = page->mapping->host;
@@ -502,75 +504,35 @@ int ecryptfs_encrypt_page(struct page *page)
"encrypted extent\n");
goto out;
}
- enc_extent_virt = kmap(enc_extent_page);
+
for (extent_offset = 0;
extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
extent_offset++) {
- loff_t offset;
-
- rc = ecryptfs_encrypt_extent(enc_extent_page, crypt_stat, page,
- extent_offset);
+ rc = crypt_extent(crypt_stat, enc_extent_page, page,
+ extent_offset, ENCRYPT);
if (rc) {
printk(KERN_ERR "%s: Error encrypting extent; "
"rc = [%d]\n", __func__, rc);
goto out;
}
- ecryptfs_lower_offset_for_extent(
- &offset, ((((loff_t)page->index)
- * (PAGE_CACHE_SIZE
- / crypt_stat->extent_size))
- + extent_offset), crypt_stat);
- rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt,
- offset, crypt_stat->extent_size);
- if (rc < 0) {
- ecryptfs_printk(KERN_ERR, "Error attempting "
- "to write lower page; rc = [%d]"
- "\n", rc);
- goto out;
- }
- }
- rc = 0;
-out:
- if (enc_extent_page) {
- kunmap(enc_extent_page);
- __free_page(enc_extent_page);
}
- return rc;
-}
-static int ecryptfs_decrypt_extent(struct page *page,
- struct ecryptfs_crypt_stat *crypt_stat,
- struct page *enc_extent_page,
- unsigned long extent_offset)
-{
- loff_t extent_base;
- char extent_iv[ECRYPTFS_MAX_IV_BYTES];
- int rc;
-
- extent_base = (((loff_t)page->index)
- * (PAGE_CACHE_SIZE / crypt_stat->extent_size));
- rc = ecryptfs_derive_iv(extent_iv, crypt_stat,
- (extent_base + extent_offset));
- if (rc) {
- ecryptfs_printk(KERN_ERR, "Error attempting to derive IV for "
- "extent [0x%.16llx]; rc = [%d]\n",
- (unsigned long long)(extent_base + extent_offset), rc);
- goto out;
- }
- rc = ecryptfs_decrypt_page_offset(crypt_stat, page,
- (extent_offset
- * crypt_stat->extent_size),
- enc_extent_page, 0,
- crypt_stat->extent_size, extent_iv);
+ lower_offset = lower_offset_for_page(crypt_stat, page);
+ enc_extent_virt = kmap(enc_extent_page);
+ rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset,
+ PAGE_CACHE_SIZE);
+ kunmap(enc_extent_page);
if (rc < 0) {
- printk(KERN_ERR "%s: Error attempting to decrypt to page with "
- "page->index = [%ld], extent_offset = [%ld]; "
- "rc = [%d]\n", __func__, page->index, extent_offset,
- rc);
+ ecryptfs_printk(KERN_ERR,
+ "Error attempting to write lower page; rc = [%d]\n",
+ rc);
goto out;
}
rc = 0;
out:
+ if (enc_extent_page) {
+ __free_page(enc_extent_page);
+ }
return rc;
}
@@ -594,43 +556,33 @@ int ecryptfs_decrypt_page(struct page *page)
{
struct inode *ecryptfs_inode;
struct ecryptfs_crypt_stat *crypt_stat;
- char *enc_extent_virt;
- struct page *enc_extent_page = NULL;
+ char *page_virt;
unsigned long extent_offset;
+ loff_t lower_offset;
int rc = 0;
ecryptfs_inode = page->mapping->host;
crypt_stat =
&(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat);
BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED));
- enc_extent_page = alloc_page(GFP_USER);
- if (!enc_extent_page) {
- rc = -ENOMEM;
- ecryptfs_printk(KERN_ERR, "Error allocating memory for "
- "encrypted extent\n");
+
+ lower_offset = lower_offset_for_page(crypt_stat, page);
+ page_virt = kmap(page);
+ rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_CACHE_SIZE,
+ ecryptfs_inode);
+ kunmap(page);
+ if (rc < 0) {
+ ecryptfs_printk(KERN_ERR,
+ "Error attempting to read lower page; rc = [%d]\n",
+ rc);
goto out;
}
- enc_extent_virt = kmap(enc_extent_page);
+
for (extent_offset = 0;
extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
extent_offset++) {
- loff_t offset;
-
- ecryptfs_lower_offset_for_extent(
- &offset, ((page->index * (PAGE_CACHE_SIZE
- / crypt_stat->extent_size))
- + extent_offset), crypt_stat);
- rc = ecryptfs_read_lower(enc_extent_virt, offset,
- crypt_stat->extent_size,
- ecryptfs_inode);
- if (rc < 0) {
- ecryptfs_printk(KERN_ERR, "Error attempting "
- "to read lower page; rc = [%d]"
- "\n", rc);
- goto out;
- }
- rc = ecryptfs_decrypt_extent(page, crypt_stat, enc_extent_page,
- extent_offset);
+ rc = crypt_extent(crypt_stat, page, page,
+ extent_offset, DECRYPT);
if (rc) {
printk(KERN_ERR "%s: Error encrypting extent; "
"rc = [%d]\n", __func__, rc);
@@ -638,140 +590,7 @@ int ecryptfs_decrypt_page(struct page *page)
}
}
out:
- if (enc_extent_page) {
- kunmap(enc_extent_page);
- __free_page(enc_extent_page);
- }
- return rc;
-}
-
-/**
- * decrypt_scatterlist
- * @crypt_stat: Cryptographic context
- * @dest_sg: The destination scatterlist to decrypt into
- * @src_sg: The source scatterlist to decrypt from
- * @size: The number of bytes to decrypt
- * @iv: The initialization vector to use for the decryption
- *
- * Returns the number of bytes decrypted; negative value on error
- */
-static int decrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
- struct scatterlist *dest_sg,
- struct scatterlist *src_sg, int size,
- unsigned char *iv)
-{
- struct ablkcipher_request *req = NULL;
- struct extent_crypt_result ecr;
- int rc = 0;
-
- BUG_ON(!crypt_stat || !crypt_stat->tfm
- || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
- if (unlikely(ecryptfs_verbosity > 0)) {
- ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
- crypt_stat->key_size);
- ecryptfs_dump_hex(crypt_stat->key,
- crypt_stat->key_size);
- }
-
- init_completion(&ecr.completion);
-
- mutex_lock(&crypt_stat->cs_tfm_mutex);
- req = ablkcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
- if (!req) {
- mutex_unlock(&crypt_stat->cs_tfm_mutex);
- rc = -ENOMEM;
- goto out;
- }
-
- ablkcipher_request_set_callback(req,
- CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- extent_crypt_complete, &ecr);
- /* Consider doing this once, when the file is opened */
- if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) {
- rc = crypto_ablkcipher_setkey(crypt_stat->tfm, crypt_stat->key,
- crypt_stat->key_size);
- if (rc) {
- ecryptfs_printk(KERN_ERR,
- "Error setting key; rc = [%d]\n",
- rc);
- mutex_unlock(&crypt_stat->cs_tfm_mutex);
- rc = -EINVAL;
- goto out;
- }
- crypt_stat->flags |= ECRYPTFS_KEY_SET;
- }
- mutex_unlock(&crypt_stat->cs_tfm_mutex);
- ecryptfs_printk(KERN_DEBUG, "Decrypting [%d] bytes.\n", size);
- ablkcipher_request_set_crypt(req, src_sg, dest_sg, size, iv);
- rc = crypto_ablkcipher_decrypt(req);
- if (rc == -EINPROGRESS || rc == -EBUSY) {
- struct extent_crypt_result *ecr = req->base.data;
-
- wait_for_completion(&ecr->completion);
- rc = ecr->rc;
- INIT_COMPLETION(ecr->completion);
- }
-out:
- ablkcipher_request_free(req);
return rc;
-
-}
-
-/**
- * ecryptfs_encrypt_page_offset
- * @crypt_stat: The cryptographic context
- * @dst_page: The page to encrypt into
- * @dst_offset: The offset in the page to encrypt into
- * @src_page: The page to encrypt from
- * @src_offset: The offset in the page to encrypt from
- * @size: The number of bytes to encrypt
- * @iv: The initialization vector to use for the encryption
- *
- * Returns the number of bytes encrypted
- */
-static int
-ecryptfs_encrypt_page_offset(struct ecryptfs_crypt_stat *crypt_stat,
- struct page *dst_page, int dst_offset,
- struct page *src_page, int src_offset, int size,
- unsigned char *iv)
-{
- struct scatterlist src_sg, dst_sg;
-
- sg_init_table(&src_sg, 1);
- sg_init_table(&dst_sg, 1);
-
- sg_set_page(&src_sg, src_page, size, src_offset);
- sg_set_page(&dst_sg, dst_page, size, dst_offset);
- return encrypt_scatterlist(crypt_stat, &dst_sg, &src_sg, size, iv);
-}
-
-/**
- * ecryptfs_decrypt_page_offset
- * @crypt_stat: The cryptographic context
- * @dst_page: The page to decrypt into
- * @dst_offset: The offset in the page to decrypt into
- * @src_page: The page to decrypt from
- * @src_offset: The offset in the page to decrypt from
- * @size: The number of bytes to decrypt
- * @iv: The initialization vector to use for the decryption
- *
- * Returns the number of bytes decrypted
- */
-static int
-ecryptfs_decrypt_page_offset(struct ecryptfs_crypt_stat *crypt_stat,
- struct page *dst_page, int dst_offset,
- struct page *src_page, int src_offset, int size,
- unsigned char *iv)
-{
- struct scatterlist src_sg, dst_sg;
-
- sg_init_table(&src_sg, 1);
- sg_set_page(&src_sg, src_page, size, src_offset);
-
- sg_init_table(&dst_sg, 1);
- sg_set_page(&dst_sg, dst_page, size, dst_offset);
-
- return decrypt_scatterlist(crypt_stat, &dst_sg, &src_sg, size, iv);
}
#define ECRYPTFS_MAX_SCATTERLIST_LEN 4
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 24f1105..992cf95 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -49,7 +49,7 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
unsigned long nr_segs, loff_t pos)
{
ssize_t rc;
- struct path lower;
+ struct path *path;
struct file *file = iocb->ki_filp;
rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
@@ -60,9 +60,8 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
if (-EIOCBQUEUED == rc)
rc = wait_on_sync_kiocb(iocb);
if (rc >= 0) {
- lower.dentry = ecryptfs_dentry_to_lower(file->f_path.dentry);
- lower.mnt = ecryptfs_dentry_to_lower_mnt(file->f_path.dentry);
- touch_atime(&lower);
+ path = ecryptfs_dentry_to_lower_path(file->f_path.dentry);
+ touch_atime(path);
}
return rc;
}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index e924cf4..eb1c597 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -120,16 +120,15 @@ static int ecryptfs_init_lower_file(struct dentry *dentry,
struct file **lower_file)
{
const struct cred *cred = current_cred();
- struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
- struct vfsmount *lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
+ struct path *path = ecryptfs_dentry_to_lower_path(dentry);
int rc;
- rc = ecryptfs_privileged_open(lower_file, lower_dentry, lower_mnt,
+ rc = ecryptfs_privileged_open(lower_file, path->dentry, path->mnt,
cred);
if (rc) {
printk(KERN_ERR "Error opening lower file "
"for lower_dentry [0x%p] and lower_mnt [0x%p]; "
- "rc = [%d]\n", lower_dentry, lower_mnt, rc);
+ "rc = [%d]\n", path->dentry, path->mnt, rc);
(*lower_file) = NULL;
}
return rc;
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 49ff8ea0..e57380e 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -247,14 +247,13 @@ int ecryptfs_process_response(struct ecryptfs_daemon *daemon,
goto unlock;
}
msg_size = (sizeof(*msg) + msg->data_len);
- msg_ctx->msg = kmalloc(msg_size, GFP_KERNEL);
+ msg_ctx->msg = kmemdup(msg, msg_size, GFP_KERNEL);
if (!msg_ctx->msg) {
rc = -ENOMEM;
printk(KERN_ERR "%s: Failed to allocate [%zd] bytes of "
"GFP_KERNEL memory\n", __func__, msg_size);
goto unlock;
}
- memcpy(msg_ctx->msg, msg, msg_size);
msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_DONE;
wake_up_process(msg_ctx->task);
rc = 0;
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 9a55f53..370d7b6 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -346,8 +346,7 @@ int dbFree(struct inode *ip, s64 blkno, s64 nblocks)
printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n",
(unsigned long long) blkno,
(unsigned long long) nblocks);
- jfs_error(ip->i_sb,
- "dbFree: block to be freed is outside the map");
+ jfs_error(ip->i_sb, "block to be freed is outside the map\n");
return -EIO;
}
@@ -384,7 +383,7 @@ int dbFree(struct inode *ip, s64 blkno, s64 nblocks)
/* free the blocks. */
if ((rc = dbFreeDmap(bmp, dp, blkno, nb))) {
- jfs_error(ip->i_sb, "dbFree: error in block map\n");
+ jfs_error(ip->i_sb, "error in block map\n");
release_metapage(mp);
IREAD_UNLOCK(ipbmap);
return (rc);
@@ -441,8 +440,7 @@ dbUpdatePMap(struct inode *ipbmap,
printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n",
(unsigned long long) blkno,
(unsigned long long) nblocks);
- jfs_error(ipbmap->i_sb,
- "dbUpdatePMap: blocks are outside the map");
+ jfs_error(ipbmap->i_sb, "blocks are outside the map\n");
return -EIO;
}
@@ -726,7 +724,7 @@ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results)
/* the hint should be within the map */
if (hint >= mapSize) {
- jfs_error(ip->i_sb, "dbAlloc: the hint is outside the map");
+ jfs_error(ip->i_sb, "the hint is outside the map\n");
return -EIO;
}
@@ -1057,8 +1055,7 @@ static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks)
bmp = sbi->bmap;
if (lastblkno < 0 || lastblkno >= bmp->db_mapsize) {
IREAD_UNLOCK(ipbmap);
- jfs_error(ip->i_sb,
- "dbExtend: the block is outside the filesystem");
+ jfs_error(ip->i_sb, "the block is outside the filesystem\n");
return -EIO;
}
@@ -1134,8 +1131,7 @@ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno,
u32 mask;
if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocNext: Corrupt dmap page");
+ jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n");
return -EIO;
}
@@ -1265,8 +1261,7 @@ dbAllocNear(struct bmap * bmp,
s8 *leaf;
if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocNear: Corrupt dmap page");
+ jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n");
return -EIO;
}
@@ -1381,8 +1376,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
*/
if (l2nb > bmp->db_agl2size) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: allocation request is larger than the "
- "allocation group size");
+ "allocation request is larger than the allocation group size\n");
return -EIO;
}
@@ -1417,7 +1411,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
(unsigned long long) blkno,
(unsigned long long) nblocks);
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: dbAllocCtl failed in free AG");
+ "dbAllocCtl failed in free AG\n");
}
return (rc);
}
@@ -1433,8 +1427,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
budmin = dcp->budmin;
if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: Corrupt dmapctl page");
+ jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n");
release_metapage(mp);
return -EIO;
}
@@ -1475,7 +1468,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
}
if (n == 4) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: failed descending stree");
+ "failed descending stree\n");
release_metapage(mp);
return -EIO;
}
@@ -1515,8 +1508,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
&blkno))) {
if (rc == -ENOSPC) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: control page "
- "inconsistent");
+ "control page inconsistent\n");
return -EIO;
}
return (rc);
@@ -1528,7 +1520,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results);
if (rc == -ENOSPC) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAG: unable to allocate blocks");
+ "unable to allocate blocks\n");
rc = -EIO;
}
return (rc);
@@ -1587,8 +1579,7 @@ static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results)
*/
rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results);
if (rc == -ENOSPC) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocAny: unable to allocate blocks");
+ jfs_error(bmp->db_ipbmap->i_sb, "unable to allocate blocks\n");
return -EIO;
}
return (rc);
@@ -1652,8 +1643,7 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen)
range_cnt = min_t(u64, max_ranges + 1, 32 * 1024);
totrim = kmalloc(sizeof(struct range2trim) * range_cnt, GFP_NOFS);
if (totrim == NULL) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbDiscardAG: no memory for trim array");
+ jfs_error(bmp->db_ipbmap->i_sb, "no memory for trim array\n");
IWRITE_UNLOCK(ipbmap);
return 0;
}
@@ -1682,8 +1672,7 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen)
nblocks = 1 << l2nb;
} else {
/* Trim any already allocated blocks */
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbDiscardAG: -EIO");
+ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n");
break;
}
@@ -1761,7 +1750,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno)
if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbFindCtl: Corrupt dmapctl page");
+ "Corrupt dmapctl page\n");
release_metapage(mp);
return -EIO;
}
@@ -1782,7 +1771,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno)
if (rc) {
if (lev != level) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbFindCtl: dmap inconsistent");
+ "dmap inconsistent\n");
return -EIO;
}
return -ENOSPC;
@@ -1906,7 +1895,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
if (dp->tree.stree[ROOT] != L2BPERDMAP) {
release_metapage(mp);
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocCtl: the dmap is not all free");
+ "the dmap is not all free\n");
rc = -EIO;
goto backout;
}
@@ -1953,7 +1942,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
* to indicate that we have leaked blocks.
*/
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocCtl: I/O Error: Block Leakage.");
+ "I/O Error: Block Leakage\n");
continue;
}
dp = (struct dmap *) mp->data;
@@ -1965,8 +1954,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
* to indicate that we have leaked blocks.
*/
release_metapage(mp);
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocCtl: Block Leakage.");
+ jfs_error(bmp->db_ipbmap->i_sb, "Block Leakage\n");
continue;
}
@@ -2263,8 +2251,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
for (; nwords > 0; nwords -= nw) {
if (leaf[word] < BUDMIN) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAllocBits: leaf page "
- "corrupt");
+ "leaf page corrupt\n");
break;
}
@@ -2536,8 +2523,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
dcp = (struct dmapctl *) mp->data;
if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) {
- jfs_error(bmp->db_ipbmap->i_sb,
- "dbAdjCtl: Corrupt dmapctl page");
+ jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n");
release_metapage(mp);
return -EIO;
}
@@ -2638,8 +2624,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
assert(level == bmp->db_maxlevel);
if (bmp->db_maxfreebud != oldroot) {
jfs_error(bmp->db_ipbmap->i_sb,
- "dbAdjCtl: the maximum free buddy is "
- "not the old root");
+ "the maximum free buddy is not the old root\n");
}
bmp->db_maxfreebud = dcp->stree[ROOT];
}
@@ -3481,7 +3466,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks)
p = BMAPBLKNO + nbperpage; /* L2 page */
l2mp = read_metapage(ipbmap, p, PSIZE, 0);
if (!l2mp) {
- jfs_error(ipbmap->i_sb, "dbExtendFS: L2 page could not be read");
+ jfs_error(ipbmap->i_sb, "L2 page could not be read\n");
return -EIO;
}
l2dcp = (struct dmapctl *) l2mp->data;
@@ -3646,8 +3631,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks)
}
} /* for each L1 in a L2 */
- jfs_error(ipbmap->i_sb,
- "dbExtendFS: function has not returned as expected");
+ jfs_error(ipbmap->i_sb, "function has not returned as expected\n");
errout:
if (l0mp)
release_metapage(l0mp);
@@ -3717,7 +3701,7 @@ void dbFinalizeBmap(struct inode *ipbmap)
}
if (bmp->db_agpref >= bmp->db_numag) {
jfs_error(ipbmap->i_sb,
- "cannot find ag with average freespace");
+ "cannot find ag with average freespace\n");
}
}
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 9f4ed13..8743ba9 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -124,21 +124,21 @@ struct dtsplit {
#define DT_PAGE(IP, MP) BT_PAGE(IP, MP, dtpage_t, i_dtroot)
/* get page buffer for specified block address */
-#define DT_GETPAGE(IP, BN, MP, SIZE, P, RC)\
-{\
- BT_GETPAGE(IP, BN, MP, dtpage_t, SIZE, P, RC, i_dtroot)\
- if (!(RC))\
- {\
- if (((P)->header.nextindex > (((BN)==0)?DTROOTMAXSLOT:(P)->header.maxslot)) ||\
- ((BN) && ((P)->header.maxslot > DTPAGEMAXSLOT)))\
- {\
- BT_PUTPAGE(MP);\
- jfs_error((IP)->i_sb, "DT_GETPAGE: dtree page corrupt");\
- MP = NULL;\
- RC = -EIO;\
- }\
- }\
-}
+#define DT_GETPAGE(IP, BN, MP, SIZE, P, RC) \
+do { \
+ BT_GETPAGE(IP, BN, MP, dtpage_t, SIZE, P, RC, i_dtroot); \
+ if (!(RC)) { \
+ if (((P)->header.nextindex > \
+ (((BN) == 0) ? DTROOTMAXSLOT : (P)->header.maxslot)) || \
+ ((BN) && ((P)->header.maxslot > DTPAGEMAXSLOT))) { \
+ BT_PUTPAGE(MP); \
+ jfs_error((IP)->i_sb, \
+ "DT_GETPAGE: dtree page corrupt\n"); \
+ MP = NULL; \
+ RC = -EIO; \
+ } \
+ } \
+} while (0)
/* for consistency */
#define DT_PUTPAGE(MP) BT_PUTPAGE(MP)
@@ -776,7 +776,7 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data,
/* Something's corrupted, mark filesystem dirty so
* chkdsk will fix it.
*/
- jfs_error(sb, "stack overrun in dtSearch!");
+ jfs_error(sb, "stack overrun!\n");
BT_STACK_DUMP(btstack);
rc = -EIO;
goto out;
@@ -3247,8 +3247,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
/* Sanity Check */
if (d_namleft == 0) {
jfs_error(ip->i_sb,
- "JFS:Dtree error: ino = "
- "%ld, bn=%Ld, index = %d",
+ "JFS:Dtree error: ino = %ld, bn=%lld, index = %d\n",
(long)ip->i_ino,
(long long)bn,
i);
@@ -3368,7 +3367,7 @@ static int dtReadFirst(struct inode *ip, struct btstack * btstack)
*/
if (BT_STACK_FULL(btstack)) {
DT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "dtReadFirst: btstack overrun");
+ jfs_error(ip->i_sb, "btstack overrun\n");
BT_STACK_DUMP(btstack);
return -EIO;
}
diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c
index e5fe850..2ae7d59 100644
--- a/fs/jfs/jfs_extent.c
+++ b/fs/jfs/jfs_extent.c
@@ -388,7 +388,7 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp)
if ((rc == 0) && xlen) {
if (xlen != nbperpage) {
- jfs_error(ip->i_sb, "extHint: corrupt xtree");
+ jfs_error(ip->i_sb, "corrupt xtree\n");
rc = -EIO;
}
XADaddress(xp, xaddr);
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index f7e042b..f321986 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -386,7 +386,7 @@ int diRead(struct inode *ip)
dp += rel_inode;
if (ip->i_ino != le32_to_cpu(dp->di_number)) {
- jfs_error(ip->i_sb, "diRead: i_ino != di_number");
+ jfs_error(ip->i_sb, "i_ino != di_number\n");
rc = -EIO;
} else if (le32_to_cpu(dp->di_nlink) == 0)
rc = -ESTALE;
@@ -625,7 +625,7 @@ int diWrite(tid_t tid, struct inode *ip)
if (!addressPXD(&(jfs_ip->ixpxd)) ||
(lengthPXD(&(jfs_ip->ixpxd)) !=
JFS_IP(ipimap)->i_imap->im_nbperiext)) {
- jfs_error(ip->i_sb, "diWrite: ixpxd invalid");
+ jfs_error(ip->i_sb, "ixpxd invalid\n");
return -EIO;
}
@@ -893,8 +893,7 @@ int diFree(struct inode *ip)
if (iagno >= imap->im_nextiag) {
print_hex_dump(KERN_ERR, "imap: ", DUMP_PREFIX_ADDRESS, 16, 4,
imap, 32, 0);
- jfs_error(ip->i_sb,
- "diFree: inum = %d, iagno = %d, nextiag = %d",
+ jfs_error(ip->i_sb, "inum = %d, iagno = %d, nextiag = %d\n",
(uint) inum, iagno, imap->im_nextiag);
return -EIO;
}
@@ -930,15 +929,14 @@ int diFree(struct inode *ip)
mask = HIGHORDER >> bitno;
if (!(le32_to_cpu(iagp->wmap[extno]) & mask)) {
- jfs_error(ip->i_sb,
- "diFree: wmap shows inode already free");
+ jfs_error(ip->i_sb, "wmap shows inode already free\n");
}
if (!addressPXD(&iagp->inoext[extno])) {
release_metapage(mp);
IREAD_UNLOCK(ipimap);
AG_UNLOCK(imap, agno);
- jfs_error(ip->i_sb, "diFree: invalid inoext");
+ jfs_error(ip->i_sb, "invalid inoext\n");
return -EIO;
}
@@ -950,7 +948,7 @@ int diFree(struct inode *ip)
release_metapage(mp);
IREAD_UNLOCK(ipimap);
AG_UNLOCK(imap, agno);
- jfs_error(ip->i_sb, "diFree: numfree > numinos");
+ jfs_error(ip->i_sb, "numfree > numinos\n");
return -EIO;
}
/*
@@ -1199,7 +1197,7 @@ int diFree(struct inode *ip)
* for the inode being freed.
*/
if (iagp->pmap[extno] != 0) {
- jfs_error(ip->i_sb, "diFree: the pmap does not show inode free");
+ jfs_error(ip->i_sb, "the pmap does not show inode free\n");
}
iagp->wmap[extno] = 0;
PXDlength(&iagp->inoext[extno], 0);
@@ -1518,8 +1516,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip)
release_metapage(mp);
AG_UNLOCK(imap, agno);
jfs_error(ip->i_sb,
- "diAlloc: can't find free bit "
- "in wmap");
+ "can't find free bit in wmap\n");
return -EIO;
}
@@ -1660,7 +1657,7 @@ diAllocAG(struct inomap * imap, int agno, bool dir, struct inode *ip)
numinos = imap->im_agctl[agno].numinos;
if (numfree > numinos) {
- jfs_error(ip->i_sb, "diAllocAG: numfree > numinos");
+ jfs_error(ip->i_sb, "numfree > numinos\n");
return -EIO;
}
@@ -1811,8 +1808,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip)
if (!iagp->nfreeinos) {
IREAD_UNLOCK(imap->im_ipimap);
release_metapage(mp);
- jfs_error(ip->i_sb,
- "diAllocIno: nfreeinos = 0, but iag on freelist");
+ jfs_error(ip->i_sb, "nfreeinos = 0, but iag on freelist\n");
return -EIO;
}
@@ -1824,7 +1820,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip)
IREAD_UNLOCK(imap->im_ipimap);
release_metapage(mp);
jfs_error(ip->i_sb,
- "diAllocIno: free inode not found in summary map");
+ "free inode not found in summary map\n");
return -EIO;
}
@@ -1839,7 +1835,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip)
if (rem >= EXTSPERSUM) {
IREAD_UNLOCK(imap->im_ipimap);
release_metapage(mp);
- jfs_error(ip->i_sb, "diAllocIno: no free extent found");
+ jfs_error(ip->i_sb, "no free extent found\n");
return -EIO;
}
extno = (sword << L2EXTSPERSUM) + rem;
@@ -1850,7 +1846,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip)
if (rem >= INOSPEREXT) {
IREAD_UNLOCK(imap->im_ipimap);
release_metapage(mp);
- jfs_error(ip->i_sb, "diAllocIno: free inode not found");
+ jfs_error(ip->i_sb, "free inode not found\n");
return -EIO;
}
@@ -1936,7 +1932,7 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip)
IREAD_LOCK(imap->im_ipimap, RDWRLOCK_IMAP);
if ((rc = diIAGRead(imap, iagno, &mp))) {
IREAD_UNLOCK(imap->im_ipimap);
- jfs_error(ip->i_sb, "diAllocExt: error reading iag");
+ jfs_error(ip->i_sb, "error reading iag\n");
return rc;
}
iagp = (struct iag *) mp->data;
@@ -1948,8 +1944,7 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip)
if (sword >= SMAPSZ) {
release_metapage(mp);
IREAD_UNLOCK(imap->im_ipimap);
- jfs_error(ip->i_sb,
- "diAllocExt: free ext summary map not found");
+ jfs_error(ip->i_sb, "free ext summary map not found\n");
return -EIO;
}
if (~iagp->extsmap[sword])
@@ -1962,7 +1957,7 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip)
if (rem >= EXTSPERSUM) {
release_metapage(mp);
IREAD_UNLOCK(imap->im_ipimap);
- jfs_error(ip->i_sb, "diAllocExt: free extent not found");
+ jfs_error(ip->i_sb, "free extent not found\n");
return -EIO;
}
extno = (sword << L2EXTSPERSUM) + rem;
@@ -2081,8 +2076,7 @@ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino)
if (bmp)
release_metapage(bmp);
- jfs_error(imap->im_ipimap->i_sb,
- "diAllocBit: iag inconsistent");
+ jfs_error(imap->im_ipimap->i_sb, "iag inconsistent\n");
return -EIO;
}
@@ -2189,7 +2183,7 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno)
/* better have free extents.
*/
if (!iagp->nfreeexts) {
- jfs_error(imap->im_ipimap->i_sb, "diNewExt: no free extents");
+ jfs_error(imap->im_ipimap->i_sb, "no free extents\n");
return -EIO;
}
@@ -2261,7 +2255,7 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno)
}
if (ciagp == NULL) {
jfs_error(imap->im_ipimap->i_sb,
- "diNewExt: ciagp == NULL");
+ "ciagp == NULL\n");
rc = -EIO;
goto error_out;
}
@@ -2498,7 +2492,7 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp)
IWRITE_UNLOCK(ipimap);
IAGFREE_UNLOCK(imap);
jfs_error(imap->im_ipimap->i_sb,
- "diNewIAG: ipimap->i_size is wrong");
+ "ipimap->i_size is wrong\n");
return -EIO;
}
@@ -2758,8 +2752,7 @@ diUpdatePMap(struct inode *ipimap,
iagno = INOTOIAG(inum);
/* make sure that the iag is contained within the map */
if (iagno >= imap->im_nextiag) {
- jfs_error(ipimap->i_sb,
- "diUpdatePMap: the iag is outside the map");
+ jfs_error(ipimap->i_sb, "the iag is outside the map\n");
return -EIO;
}
/* read the iag */
@@ -2788,13 +2781,13 @@ diUpdatePMap(struct inode *ipimap,
*/
if (!(le32_to_cpu(iagp->wmap[extno]) & mask)) {
jfs_error(ipimap->i_sb,
- "diUpdatePMap: inode %ld not marked as "
- "allocated in wmap!", inum);
+ "inode %ld not marked as allocated in wmap!\n",
+ inum);
}
if (!(le32_to_cpu(iagp->pmap[extno]) & mask)) {
jfs_error(ipimap->i_sb,
- "diUpdatePMap: inode %ld not marked as "
- "allocated in pmap!", inum);
+ "inode %ld not marked as allocated in pmap!\n",
+ inum);
}
/* update the bitmap for the extent of the freed inode */
iagp->pmap[extno] &= cpu_to_le32(~mask);
@@ -2809,15 +2802,13 @@ diUpdatePMap(struct inode *ipimap,
if (!(le32_to_cpu(iagp->wmap[extno]) & mask)) {
release_metapage(mp);
jfs_error(ipimap->i_sb,
- "diUpdatePMap: the inode is not allocated in "
- "the working map");
+ "the inode is not allocated in the working map\n");
return -EIO;
}
if ((le32_to_cpu(iagp->pmap[extno]) & mask) != 0) {
release_metapage(mp);
jfs_error(ipimap->i_sb,
- "diUpdatePMap: the inode is not free in the "
- "persistent map");
+ "the inode is not free in the persistent map\n");
return -EIO;
}
/* update the bitmap for the extent of the allocated inode */
@@ -2909,8 +2900,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap)
iagp = (struct iag *) bp->data;
if (le32_to_cpu(iagp->iagnum) != i) {
release_metapage(bp);
- jfs_error(ipimap->i_sb,
- "diExtendFs: unexpected value of iagnum");
+ jfs_error(ipimap->i_sb, "unexpected value of iagnum\n");
return -EIO;
}
@@ -2986,8 +2976,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap)
if (xnuminos != atomic_read(&imap->im_numinos) ||
xnumfree != atomic_read(&imap->im_numfree)) {
- jfs_error(ipimap->i_sb,
- "diExtendFs: numinos or numfree incorrect");
+ jfs_error(ipimap->i_sb, "numinos or numfree incorrect\n");
return -EIO;
}
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 9e3aaff..d165cde 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -647,7 +647,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock,
if (mp) {
if (mp->logical_size != size) {
jfs_error(inode->i_sb,
- "__get_metapage: mp->logical_size != size");
+ "get_mp->logical_size != size\n");
jfs_err("logical_size = %d, size = %d",
mp->logical_size, size);
dump_stack();
@@ -658,8 +658,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock,
if (test_bit(META_discard, &mp->flag)) {
if (!new) {
jfs_error(inode->i_sb,
- "__get_metapage: using a "
- "discarded metapage");
+ "using a discarded metapage\n");
discard_metapage(mp);
goto unlock;
}
diff --git a/fs/jfs/jfs_superblock.h b/fs/jfs/jfs_superblock.h
index 884fc21..04847b8 100644
--- a/fs/jfs/jfs_superblock.h
+++ b/fs/jfs/jfs_superblock.h
@@ -108,6 +108,7 @@ struct jfs_superblock {
extern int readSuper(struct super_block *, struct buffer_head **);
extern int updateSuper(struct super_block *, uint);
+__printf(2, 3)
extern void jfs_error(struct super_block *, const char *, ...);
extern int jfs_mount(struct super_block *);
extern int jfs_mount_rw(struct super_block *, int);
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 5fcc02e..564c4f2 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2684,7 +2684,7 @@ void txAbort(tid_t tid, int dirty)
* mark filesystem dirty
*/
if (dirty)
- jfs_error(tblk->sb, "txAbort");
+ jfs_error(tblk->sb, "\n");
return;
}
diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c
index 6c50871..5ad7748 100644
--- a/fs/jfs/jfs_xtree.c
+++ b/fs/jfs/jfs_xtree.c
@@ -64,22 +64,23 @@
/* get page buffer for specified block address */
/* ToDo: Replace this ugly macro with a function */
-#define XT_GETPAGE(IP, BN, MP, SIZE, P, RC)\
-{\
- BT_GETPAGE(IP, BN, MP, xtpage_t, SIZE, P, RC, i_xtroot)\
- if (!(RC))\
- {\
- if ((le16_to_cpu((P)->header.nextindex) < XTENTRYSTART) ||\
- (le16_to_cpu((P)->header.nextindex) > le16_to_cpu((P)->header.maxentry)) ||\
- (le16_to_cpu((P)->header.maxentry) > (((BN)==0)?XTROOTMAXSLOT:PSIZE>>L2XTSLOTSIZE)))\
- {\
- jfs_error((IP)->i_sb, "XT_GETPAGE: xtree page corrupt");\
- BT_PUTPAGE(MP);\
- MP = NULL;\
- RC = -EIO;\
- }\
- }\
-}
+#define XT_GETPAGE(IP, BN, MP, SIZE, P, RC) \
+do { \
+ BT_GETPAGE(IP, BN, MP, xtpage_t, SIZE, P, RC, i_xtroot); \
+ if (!(RC)) { \
+ if ((le16_to_cpu((P)->header.nextindex) < XTENTRYSTART) || \
+ (le16_to_cpu((P)->header.nextindex) > \
+ le16_to_cpu((P)->header.maxentry)) || \
+ (le16_to_cpu((P)->header.maxentry) > \
+ (((BN) == 0) ? XTROOTMAXSLOT : PSIZE >> L2XTSLOTSIZE))) { \
+ jfs_error((IP)->i_sb, \
+ "XT_GETPAGE: xtree page corrupt\n"); \
+ BT_PUTPAGE(MP); \
+ MP = NULL; \
+ RC = -EIO; \
+ } \
+ } \
+} while (0)
/* for consistency */
#define XT_PUTPAGE(MP) BT_PUTPAGE(MP)
@@ -499,7 +500,7 @@ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp,
/* push (bn, index) of the parent page/entry */
if (BT_STACK_FULL(btstack)) {
- jfs_error(ip->i_sb, "stack overrun in xtSearch!");
+ jfs_error(ip->i_sb, "stack overrun!\n");
XT_PUTPAGE(mp);
return -EIO;
}
@@ -1385,7 +1386,7 @@ int xtExtend(tid_t tid, /* transaction id */
if (cmp != 0) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtExtend: xtSearch did not find extent");
+ jfs_error(ip->i_sb, "xtSearch did not find extent\n");
return -EIO;
}
@@ -1393,7 +1394,7 @@ int xtExtend(tid_t tid, /* transaction id */
xad = &p->xad[index];
if ((offsetXAD(xad) + lengthXAD(xad)) != xoff) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtExtend: extension is not contiguous");
+ jfs_error(ip->i_sb, "extension is not contiguous\n");
return -EIO;
}
@@ -1552,7 +1553,7 @@ printf("xtTailgate: nxoff:0x%lx nxlen:0x%x nxaddr:0x%lx\n",
if (cmp != 0) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtTailgate: couldn't find extent");
+ jfs_error(ip->i_sb, "couldn't find extent\n");
return -EIO;
}
@@ -1560,8 +1561,7 @@ printf("xtTailgate: nxoff:0x%lx nxlen:0x%x nxaddr:0x%lx\n",
nextindex = le16_to_cpu(p->header.nextindex);
if (index != nextindex - 1) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb,
- "xtTailgate: the entry found is not the last entry");
+ jfs_error(ip->i_sb, "the entry found is not the last entry\n");
return -EIO;
}
@@ -1734,7 +1734,7 @@ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad)
if (cmp != 0) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtUpdate: Could not find extent");
+ jfs_error(ip->i_sb, "Could not find extent\n");
return -EIO;
}
@@ -1758,7 +1758,7 @@ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad)
(nxoff + nxlen > xoff + xlen)) {
XT_PUTPAGE(mp);
jfs_error(ip->i_sb,
- "xtUpdate: nXAD in not completely contained within XAD");
+ "nXAD in not completely contained within XAD\n");
return -EIO;
}
@@ -1907,7 +1907,7 @@ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad)
if (xoff >= nxoff) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtUpdate: xoff >= nxoff");
+ jfs_error(ip->i_sb, "xoff >= nxoff\n");
return -EIO;
}
/* #endif _JFS_WIP_COALESCE */
@@ -2048,14 +2048,13 @@ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad)
if (cmp != 0) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb, "xtUpdate: xtSearch failed");
+ jfs_error(ip->i_sb, "xtSearch failed\n");
return -EIO;
}
if (index0 != index) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb,
- "xtUpdate: unexpected value of index");
+ jfs_error(ip->i_sb, "unexpected value of index\n");
return -EIO;
}
}
@@ -3650,7 +3649,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag)
getChild:
/* save current parent entry for the child page */
if (BT_STACK_FULL(&btstack)) {
- jfs_error(ip->i_sb, "stack overrun in xtTruncate!");
+ jfs_error(ip->i_sb, "stack overrun!\n");
XT_PUTPAGE(mp);
return -EIO;
}
@@ -3751,8 +3750,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size)
if (cmp != 0) {
XT_PUTPAGE(mp);
- jfs_error(ip->i_sb,
- "xtTruncate_pmap: did not find extent");
+ jfs_error(ip->i_sb, "did not find extent\n");
return -EIO;
}
} else {
@@ -3851,7 +3849,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size)
getChild:
/* save current parent entry for the child page */
if (BT_STACK_FULL(&btstack)) {
- jfs_error(ip->i_sb, "stack overrun in xtTruncate_pmap!");
+ jfs_error(ip->i_sb, "stack overrun!\n");
XT_PUTPAGE(mp);
return -EIO;
}
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 8b19027..aa8a337 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1176,7 +1176,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!S_ISDIR(old_ip->i_mode) && new_ip)
IWRITE_UNLOCK(new_ip);
jfs_error(new_ip->i_sb,
- "jfs_rename: new_ip->i_nlink != 0");
+ "new_ip->i_nlink != 0\n");
return -EIO;
}
tblk = tid_to_tblock(tid);
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 8d0c1c7..90b3bc2 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -530,7 +530,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
goto resume;
error_out:
- jfs_error(sb, "jfs_extendfs");
+ jfs_error(sb, "\n");
resume:
/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 788e0a9..6669aa2 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -92,16 +92,20 @@ static void jfs_handle_error(struct super_block *sb)
/* nothing is done for continue beyond marking the superblock dirty */
}
-void jfs_error(struct super_block *sb, const char * function, ...)
+void jfs_error(struct super_block *sb, const char *fmt, ...)
{
- static char error_buf[256];
+ struct va_format vaf;
va_list args;
- va_start(args, function);
- vsnprintf(error_buf, sizeof(error_buf), function, args);
- va_end(args);
+ va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
- pr_err("ERROR: (device %s): %s\n", sb->s_id, error_buf);
+ pr_err("ERROR: (device %s): %pf: %pV\n",
+ sb->s_id, __builtin_return_address(0), &vaf);
+
+ va_end(args);
jfs_handle_error(sb);
}
@@ -617,7 +621,7 @@ static int jfs_freeze(struct super_block *sb)
txQuiesce(sb);
rc = lmLogShutdown(log);
if (rc) {
- jfs_error(sb, "jfs_freeze: lmLogShutdown failed");
+ jfs_error(sb, "lmLogShutdown failed\n");
/* let operations fail rather than hang */
txResume(sb);
@@ -646,12 +650,12 @@ static int jfs_unfreeze(struct super_block *sb)
if (!(sb->s_flags & MS_RDONLY)) {
rc = updateSuper(sb, FM_MOUNT);
if (rc) {
- jfs_error(sb, "jfs_unfreeze: updateSuper failed");
+ jfs_error(sb, "updateSuper failed\n");
goto out;
}
rc = lmLogInit(log);
if (rc)
- jfs_error(sb, "jfs_unfreeze: lmLogInit failed");
+ jfs_error(sb, "lmLogInit failed\n");
out:
txResume(sb);
}
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 42d67f9..d3472f4 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -382,7 +382,7 @@ static int ea_read(struct inode *ip, struct jfs_ea_list *ealist)
nbytes = sizeDXD(&ji->ea);
if (!nbytes) {
- jfs_error(sb, "ea_read: nbytes is 0");
+ jfs_error(sb, "nbytes is 0\n");
return -EIO;
}
@@ -482,7 +482,7 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size)
current_blocks = 0;
} else {
if (!(ji->ea.flag & DXD_EXTENT)) {
- jfs_error(sb, "ea_get: invalid ea.flag)");
+ jfs_error(sb, "invalid ea.flag\n");
return -EIO;
}
current_blocks = (ea_size + sb->s_blocksize - 1) >>
@@ -1089,8 +1089,8 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
}
#ifdef CONFIG_JFS_SECURITY
-int jfs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
- void *fs_info)
+static int jfs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *fs_info)
{
const struct xattr *xattr;
tid_t *tid = fs_info;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 430b687..dc8f1ef 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -81,6 +81,22 @@ config NFSD_V4
If unsure, say N.
+config NFSD_V4_SECURITY_LABEL
+ bool "Provide Security Label support for NFSv4 server"
+ depends on NFSD_V4 && SECURITY
+ help
+
+ Say Y here if you want enable fine-grained security label attribute
+ support for NFS version 4. Security labels allow security modules like
+ SELinux and Smack to label files to facilitate enforcement of their policies.
+ Without this an NFSv4 mount will have the same label on each file.
+
+ If you do not wish to enable fine-grained security labels SELinux or
+ Smack policies on NFSv4 files, say N.
+
+ WARNING: there is still a chance of backwards-incompatible protocol changes.
+ For now we recommend "Y" only for developers and testers."
+
config NFSD_FAULT_INJECTION
bool "NFS server manual fault injection"
depends on NFSD_V4 && DEBUG_KERNEL
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 27d74a2..a7cee86 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -42,6 +42,36 @@
#include "current_stateid.h"
#include "netns.h"
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#include <linux/security.h>
+
+static inline void
+nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
+{
+ struct inode *inode = resfh->fh_dentry->d_inode;
+ int status;
+
+ mutex_lock(&inode->i_mutex);
+ status = security_inode_setsecctx(resfh->fh_dentry,
+ label->data, label->len);
+ mutex_unlock(&inode->i_mutex);
+
+ if (status)
+ /*
+ * XXX: We should really fail the whole open, but we may
+ * already have created a new file, so it may be too
+ * late. For now this seems the least of evils:
+ */
+ bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+
+ return;
+}
+#else
+static inline void
+nfsd4_security_inode_setsecctx(struct svc_fh *resfh, struct xdr_netobj *label, u32 *bmval)
+{ }
+#endif
+
#define NFSDDBG_FACILITY NFSDDBG_PROC
static u32 nfsd_attrmask[] = {
@@ -239,6 +269,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
(u32 *)open->op_verf.data,
&open->op_truncate, &open->op_created);
+ if (!status && open->op_label.len)
+ nfsd4_security_inode_setsecctx(resfh, &open->op_label, open->op_bmval);
+
/*
* Following rfc 3530 14.2.16, use the returned bitmask
* to indicate which attributes we used to store the
@@ -263,7 +296,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
nfsd4_set_open_owner_reply_cache(cstate, open, resfh);
accmode = NFSD_MAY_NOP;
- if (open->op_created)
+ if (open->op_created ||
+ open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
accmode |= NFSD_MAY_OWNER_OVERRIDE;
status = do_open_permission(rqstp, resfh, open, accmode);
set_change_info(&open->op_cinfo, current_fh);
@@ -637,6 +671,9 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
+ if (create->cr_label.len)
+ nfsd4_security_inode_setsecctx(&resfh, &create->cr_label, create->cr_bmval);
+
if (create->cr_acl != NULL)
do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
create->cr_bmval);
@@ -916,6 +953,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
setattr->sa_acl);
if (status)
goto out;
+ if (setattr->sa_label.len)
+ status = nfsd4_set_nfs4_label(rqstp, &cstate->current_fh,
+ &setattr->sa_label);
+ if (status)
+ goto out;
status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
0, (time_t)0);
out:
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f170518..280acef 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -97,19 +97,20 @@ nfs4_lock_state(void)
static void free_session(struct nfsd4_session *);
-void nfsd4_put_session(struct nfsd4_session *ses)
+static bool is_session_dead(struct nfsd4_session *ses)
{
- atomic_dec(&ses->se_ref);
+ return ses->se_flags & NFS4_SESSION_DEAD;
}
-static bool is_session_dead(struct nfsd4_session *ses)
+void nfsd4_put_session(struct nfsd4_session *ses)
{
- return ses->se_flags & NFS4_SESSION_DEAD;
+ if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
+ free_session(ses);
}
-static __be32 mark_session_dead_locked(struct nfsd4_session *ses)
+static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me)
{
- if (atomic_read(&ses->se_ref))
+ if (atomic_read(&ses->se_ref) > ref_held_by_me)
return nfserr_jukebox;
ses->se_flags |= NFS4_SESSION_DEAD;
return nfs_ok;
@@ -364,19 +365,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
}
static struct nfs4_delegation *
-alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh, u32 type)
+alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh)
{
struct nfs4_delegation *dp;
struct nfs4_file *fp = stp->st_file;
dprintk("NFSD alloc_init_deleg\n");
- /*
- * Major work on the lease subsystem (for example, to support
- * calbacks on stat) will be required before we can support
- * write delegations properly.
- */
- if (type != NFS4_OPEN_DELEGATE_READ)
- return NULL;
if (fp->fi_had_conflict)
return NULL;
if (num_delegations > max_delegations)
@@ -397,7 +391,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
INIT_LIST_HEAD(&dp->dl_recall_lru);
get_nfs4_file(fp);
dp->dl_file = fp;
- dp->dl_type = type;
+ dp->dl_type = NFS4_OPEN_DELEGATE_READ;
fh_copy_shallow(&dp->dl_fh, &current_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
@@ -1188,6 +1182,9 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source)
target->cr_gid = source->cr_gid;
target->cr_group_info = source->cr_group_info;
get_group_info(target->cr_group_info);
+ target->cr_gss_mech = source->cr_gss_mech;
+ if (source->cr_gss_mech)
+ gss_mech_get(source->cr_gss_mech);
return 0;
}
@@ -1262,6 +1259,31 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
return 0 == strcmp(cr1->cr_principal, cr2->cr_principal);
}
+static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
+{
+ struct svc_cred *cr = &rqstp->rq_cred;
+ u32 service;
+
+ service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor);
+ return service == RPC_GSS_SVC_INTEGRITY ||
+ service == RPC_GSS_SVC_PRIVACY;
+}
+
+static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
+{
+ struct svc_cred *cr = &rqstp->rq_cred;
+
+ if (!cl->cl_mach_cred)
+ return true;
+ if (cl->cl_cred.cr_gss_mech != cr->cr_gss_mech)
+ return false;
+ if (!svc_rqst_integrity_protected(rqstp))
+ return false;
+ if (!cr->cr_principal)
+ return false;
+ return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
+}
+
static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
{
static u32 current_clientid = 1;
@@ -1639,16 +1661,16 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
if (exid->flags & ~EXCHGID4_FLAG_MASK_A)
return nfserr_inval;
- /* Currently only support SP4_NONE */
switch (exid->spa_how) {
+ case SP4_MACH_CRED:
+ if (!svc_rqst_integrity_protected(rqstp))
+ return nfserr_inval;
case SP4_NONE:
break;
default: /* checked by xdr code */
WARN_ON_ONCE(1);
case SP4_SSV:
return nfserr_encr_alg_unsupp;
- case SP4_MACH_CRED:
- return nfserr_serverfault; /* no excuse :-/ */
}
/* Cases below refer to rfc 5661 section 18.35.4: */
@@ -1663,6 +1685,10 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
status = nfserr_inval;
goto out;
}
+ if (!mach_creds_match(conf, rqstp)) {
+ status = nfserr_wrong_cred;
+ goto out;
+ }
if (!creds_match) { /* case 9 */
status = nfserr_perm;
goto out;
@@ -1709,7 +1735,8 @@ out_new:
status = nfserr_jukebox;
goto out;
}
- new->cl_minorversion = 1;
+ new->cl_minorversion = cstate->minorversion;
+ new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
gen_clid(new, nn);
add_to_unconfirmed(new);
@@ -1839,6 +1866,24 @@ static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
return nfs_ok;
}
+static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs)
+{
+ switch (cbs->flavor) {
+ case RPC_AUTH_NULL:
+ case RPC_AUTH_UNIX:
+ return nfs_ok;
+ default:
+ /*
+ * GSS case: the spec doesn't allow us to return this
+ * error. But it also doesn't allow us not to support
+ * GSS.
+ * I'd rather this fail hard than return some error the
+ * client might think it can already handle:
+ */
+ return nfserr_encr_alg_unsupp;
+ }
+}
+
__be32
nfsd4_create_session(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
@@ -1854,6 +1899,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
return nfserr_inval;
+ status = nfsd4_check_cb_sec(&cr_ses->cb_sec);
+ if (status)
+ return status;
status = check_forechannel_attrs(&cr_ses->fore_channel, nn);
if (status)
return status;
@@ -1874,6 +1922,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
WARN_ON_ONCE(conf && unconf);
if (conf) {
+ status = nfserr_wrong_cred;
+ if (!mach_creds_match(conf, rqstp))
+ goto out_free_conn;
cs_slot = &conf->cl_cs_slot;
status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
if (status == nfserr_replay_cache) {
@@ -1890,6 +1941,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
status = nfserr_clid_inuse;
goto out_free_conn;
}
+ status = nfserr_wrong_cred;
+ if (!mach_creds_match(unconf, rqstp))
+ goto out_free_conn;
cs_slot = &unconf->cl_cs_slot;
status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
if (status) {
@@ -1957,7 +2011,11 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state
{
struct nfsd4_session *session = cstate->session;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ __be32 status;
+ status = nfsd4_check_cb_sec(&bc->bc_cb_sec);
+ if (status)
+ return status;
spin_lock(&nn->client_lock);
session->se_cb_prog = bc->bc_cb_program;
session->se_cb_sec = bc->bc_cb_sec;
@@ -1986,6 +2044,9 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
status = nfserr_badsession;
if (!session)
goto out;
+ status = nfserr_wrong_cred;
+ if (!mach_creds_match(session->se_client, rqstp))
+ goto out;
status = nfsd4_map_bcts_dir(&bcts->dir);
if (status)
goto out;
@@ -2014,6 +2075,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
{
struct nfsd4_session *ses;
__be32 status;
+ int ref_held_by_me = 0;
struct nfsd_net *nn = net_generic(SVC_NET(r), nfsd_net_id);
nfs4_lock_state();
@@ -2021,6 +2083,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
if (nfsd4_compound_in_session(cstate->session, &sessionid->sessionid)) {
if (!nfsd4_last_compound_op(r))
goto out;
+ ref_held_by_me++;
}
dump_sessionid(__func__, &sessionid->sessionid);
spin_lock(&nn->client_lock);
@@ -2028,17 +2091,22 @@ nfsd4_destroy_session(struct svc_rqst *r,
status = nfserr_badsession;
if (!ses)
goto out_client_lock;
- status = mark_session_dead_locked(ses);
- if (status)
+ status = nfserr_wrong_cred;
+ if (!mach_creds_match(ses->se_client, r))
goto out_client_lock;
+ nfsd4_get_session_locked(ses);
+ status = mark_session_dead_locked(ses, 1 + ref_held_by_me);
+ if (status)
+ goto out_put_session;
unhash_session(ses);
spin_unlock(&nn->client_lock);
nfsd4_probe_callback_sync(ses->se_client);
spin_lock(&nn->client_lock);
- free_session(ses);
status = nfs_ok;
+out_put_session:
+ nfsd4_put_session(ses);
out_client_lock:
spin_unlock(&nn->client_lock);
out:
@@ -2058,26 +2126,31 @@ static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_s
return NULL;
}
-static void nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses)
+static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses)
{
struct nfs4_client *clp = ses->se_client;
struct nfsd4_conn *c;
+ __be32 status = nfs_ok;
int ret;
spin_lock(&clp->cl_lock);
c = __nfsd4_find_conn(new->cn_xprt, ses);
- if (c) {
- spin_unlock(&clp->cl_lock);
- free_conn(new);
- return;
- }
+ if (c)
+ goto out_free;
+ status = nfserr_conn_not_bound_to_session;
+ if (clp->cl_mach_cred)
+ goto out_free;
__nfsd4_hash_conn(new, ses);
spin_unlock(&clp->cl_lock);
ret = nfsd4_register_conn(new);
if (ret)
/* oops; xprt is already down: */
nfsd4_conn_lost(&new->cn_xpt_user);
- return;
+ return nfs_ok;
+out_free:
+ spin_unlock(&clp->cl_lock);
+ free_conn(new);
+ return status;
}
static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session)
@@ -2169,8 +2242,10 @@ nfsd4_sequence(struct svc_rqst *rqstp,
if (status)
goto out_put_session;
- nfsd4_sequence_check_conn(conn, session);
+ status = nfsd4_sequence_check_conn(conn, session);
conn = NULL;
+ if (status)
+ goto out_put_session;
/* Success! bump slot seqid */
slot->sl_seqid = seq->seqid;
@@ -2232,7 +2307,10 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
status = nfserr_stale_clientid;
goto out;
}
-
+ if (!mach_creds_match(clp, rqstp)) {
+ status = nfserr_wrong_cred;
+ goto out;
+ }
expire_client(clp);
out:
nfs4_unlock_state();
@@ -2940,13 +3018,13 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int f
return fl;
}
-static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
+static int nfs4_setlease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_file;
struct file_lock *fl;
int status;
- fl = nfs4_alloc_init_lease(dp, flag);
+ fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ);
if (!fl)
return -ENOMEM;
fl->fl_file = find_readable_file(fp);
@@ -2964,12 +3042,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
return 0;
}
-static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
+static int nfs4_set_delegation(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_file;
if (!fp->fi_lease)
- return nfs4_setlease(dp, flag);
+ return nfs4_setlease(dp);
spin_lock(&recall_lock);
if (fp->fi_had_conflict) {
spin_unlock(&recall_lock);
@@ -3005,6 +3083,9 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
/*
* Attempt to hand out a delegation.
+ *
+ * Note we don't support write delegations, and won't until the vfs has
+ * proper support for them.
*/
static void
nfs4_open_delegation(struct net *net, struct svc_fh *fh,
@@ -3013,39 +3094,45 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
struct nfs4_delegation *dp;
struct nfs4_openowner *oo = container_of(stp->st_stateowner, struct nfs4_openowner, oo_owner);
int cb_up;
- int status = 0, flag = 0;
+ int status = 0;
cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
- flag = NFS4_OPEN_DELEGATE_NONE;
open->op_recall = 0;
switch (open->op_claim_type) {
case NFS4_OPEN_CLAIM_PREVIOUS:
if (!cb_up)
open->op_recall = 1;
- flag = open->op_delegate_type;
- if (flag == NFS4_OPEN_DELEGATE_NONE)
- goto out;
+ if (open->op_delegate_type != NFS4_OPEN_DELEGATE_READ)
+ goto out_no_deleg;
break;
case NFS4_OPEN_CLAIM_NULL:
- /* Let's not give out any delegations till everyone's
- * had the chance to reclaim theirs.... */
+ /*
+ * Let's not give out any delegations till everyone's
+ * had the chance to reclaim theirs....
+ */
if (locks_in_grace(net))
- goto out;
+ goto out_no_deleg;
if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
- goto out;
+ goto out_no_deleg;
+ /*
+ * Also, if the file was opened for write or
+ * create, there's a good chance the client's
+ * about to write to it, resulting in an
+ * immediate recall (since we don't support
+ * write delegations):
+ */
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
- flag = NFS4_OPEN_DELEGATE_WRITE;
- else
- flag = NFS4_OPEN_DELEGATE_READ;
+ goto out_no_deleg;
+ if (open->op_create == NFS4_OPEN_CREATE)
+ goto out_no_deleg;
break;
default:
- goto out;
+ goto out_no_deleg;
}
-
- dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh, flag);
+ dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh);
if (dp == NULL)
goto out_no_deleg;
- status = nfs4_set_delegation(dp, flag);
+ status = nfs4_set_delegation(dp);
if (status)
goto out_free;
@@ -3053,24 +3140,23 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
STATEID_VAL(&dp->dl_stid.sc_stateid));
-out:
- open->op_delegate_type = flag;
- if (flag == NFS4_OPEN_DELEGATE_NONE) {
- if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
- open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
- dprintk("NFSD: WARNING: refusing delegation reclaim\n");
-
- /* 4.1 client asking for a delegation? */
- if (open->op_deleg_want)
- nfsd4_open_deleg_none_ext(open, status);
- }
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
return;
out_free:
unhash_stid(&dp->dl_stid);
nfs4_put_delegation(dp);
out_no_deleg:
- flag = NFS4_OPEN_DELEGATE_NONE;
- goto out;
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
+ if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
+ open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) {
+ dprintk("NFSD: WARNING: refusing delegation reclaim\n");
+ open->op_recall = 1;
+ }
+
+ /* 4.1 client asking for a delegation? */
+ if (open->op_deleg_want)
+ nfsd4_open_deleg_none_ext(open, status);
+ return;
}
static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
@@ -3427,7 +3513,7 @@ grace_disallows_io(struct net *net, struct inode *inode)
/* Returns true iff a is later than b: */
static bool stateid_generation_after(stateid_t *a, stateid_t *b)
{
- return (s32)a->si_generation - (s32)b->si_generation > 0;
+ return (s32)(a->si_generation - b->si_generation) > 0;
}
static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session)
@@ -4435,7 +4521,6 @@ __be32
nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_locku *locku)
{
- struct nfs4_lockowner *lo;
struct nfs4_ol_stateid *stp;
struct file *filp = NULL;
struct file_lock *file_lock = NULL;
@@ -4468,10 +4553,9 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfserr_jukebox;
goto out;
}
- lo = lockowner(stp->st_stateowner);
locks_init_lock(file_lock);
file_lock->fl_type = F_UNLCK;
- file_lock->fl_owner = (fl_owner_t)lo;
+ file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
file_lock->fl_pid = current->tgid;
file_lock->fl_file = filp;
file_lock->fl_flags = FL_POSIX;
@@ -4490,11 +4574,6 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
- if (nfsd4_has_session(cstate) && !check_for_locks(stp->st_file, lo)) {
- WARN_ON_ONCE(cstate->replay_owner);
- release_lockowner(lo);
- }
-
out:
nfsd4_bump_seqid(cstate, status);
if (!cstate->replay_owner)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 6cd86e0..0c0f3ea9 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -55,6 +55,11 @@
#include "cache.h"
#include "netns.h"
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#include <linux/security.h>
+#endif
+
+
#define NFSDDBG_FACILITY NFSDDBG_XDR
/*
@@ -134,6 +139,19 @@ xdr_error: \
} \
} while (0)
+static void next_decode_page(struct nfsd4_compoundargs *argp)
+{
+ argp->pagelist++;
+ argp->p = page_address(argp->pagelist[0]);
+ if (argp->pagelen < PAGE_SIZE) {
+ argp->end = argp->p + (argp->pagelen>>2);
+ argp->pagelen = 0;
+ } else {
+ argp->end = argp->p + (PAGE_SIZE>>2);
+ argp->pagelen -= PAGE_SIZE;
+ }
+}
+
static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
{
/* We want more bytes than seem to be available.
@@ -161,16 +179,7 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
* guarantee p points to at least nbytes bytes.
*/
memcpy(p, argp->p, avail);
- /* step to next page */
- argp->p = page_address(argp->pagelist[0]);
- argp->pagelist++;
- if (argp->pagelen < PAGE_SIZE) {
- argp->end = argp->p + (argp->pagelen>>2);
- argp->pagelen = 0;
- } else {
- argp->end = argp->p + (PAGE_SIZE>>2);
- argp->pagelen -= PAGE_SIZE;
- }
+ next_decode_page(argp);
memcpy(((char*)p)+avail, argp->p, (nbytes - avail));
argp->p += XDR_QUADLEN(nbytes - avail);
return p;
@@ -242,7 +251,8 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
static __be32
nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
- struct iattr *iattr, struct nfs4_acl **acl)
+ struct iattr *iattr, struct nfs4_acl **acl,
+ struct xdr_netobj *label)
{
int expected_len, len = 0;
u32 dummy32;
@@ -380,6 +390,32 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
goto xdr_error;
}
}
+
+ label->len = 0;
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+ if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
+ READ_BUF(4);
+ len += 4;
+ READ32(dummy32); /* lfs: we don't use it */
+ READ_BUF(4);
+ len += 4;
+ READ32(dummy32); /* pi: we don't use it either */
+ READ_BUF(4);
+ len += 4;
+ READ32(dummy32);
+ READ_BUF(dummy32);
+ if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN)
+ return nfserr_badlabel;
+ len += (XDR_QUADLEN(dummy32) << 2);
+ READMEM(buf, dummy32);
+ label->data = kzalloc(dummy32 + 1, GFP_KERNEL);
+ if (!label->data)
+ return nfserr_jukebox;
+ defer_free(argp, kfree, label->data);
+ memcpy(label->data, buf, dummy32);
+ }
+#endif
+
if (bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0
|| bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1
|| bmval[2] & ~NFSD_WRITEABLE_ATTRS_WORD2)
@@ -428,7 +464,11 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
/* callback_sec_params4 */
READ_BUF(4);
READ32(nr_secflavs);
- cbs->flavor = (u32)(-1);
+ if (nr_secflavs)
+ cbs->flavor = (u32)(-1);
+ else
+ /* Is this legal? Be generous, take it to mean AUTH_NONE: */
+ cbs->flavor = 0;
for (i = 0; i < nr_secflavs; ++i) {
READ_BUF(4);
READ32(dummy);
@@ -576,7 +616,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
return status;
status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
- &create->cr_acl);
+ &create->cr_acl, &create->cr_label);
if (status)
goto out;
@@ -827,7 +867,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
case NFS4_CREATE_UNCHECKED:
case NFS4_CREATE_GUARDED:
status = nfsd4_decode_fattr(argp, open->op_bmval,
- &open->op_iattr, &open->op_acl);
+ &open->op_iattr, &open->op_acl, &open->op_label);
if (status)
goto out;
break;
@@ -841,7 +881,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
READ_BUF(NFS4_VERIFIER_SIZE);
COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
status = nfsd4_decode_fattr(argp, open->op_bmval,
- &open->op_iattr, &open->op_acl);
+ &open->op_iattr, &open->op_acl, &open->op_label);
if (status)
goto out;
break;
@@ -1063,7 +1103,7 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta
if (status)
return status;
return nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr,
- &setattr->sa_acl);
+ &setattr->sa_acl, &setattr->sa_label);
}
static __be32
@@ -1567,6 +1607,7 @@ struct nfsd4_minorversion_ops {
static struct nfsd4_minorversion_ops nfsd4_minorversion[] = {
[0] = { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) },
[1] = { nfsd41_dec_ops, ARRAY_SIZE(nfsd41_dec_ops) },
+ [2] = { nfsd41_dec_ops, ARRAY_SIZE(nfsd41_dec_ops) },
};
static __be32
@@ -1953,6 +1994,36 @@ nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
FATTR4_WORD0_RDATTR_ERROR)
#define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+static inline __be32
+nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+{
+ __be32 *p = *pp;
+
+ if (*buflen < ((XDR_QUADLEN(len) << 2) + 4 + 4 + 4))
+ return nfserr_resource;
+
+ /*
+ * For now we use a 0 here to indicate the null translation; in
+ * the future we may place a call to translation code here.
+ */
+ if ((*buflen -= 8) < 0)
+ return nfserr_resource;
+
+ WRITE32(0); /* lfs */
+ WRITE32(0); /* pi */
+ p = xdr_encode_opaque(p, context, len);
+ *buflen -= (XDR_QUADLEN(len) << 2) + 4;
+
+ *pp = p;
+ return 0;
+}
+#else
+static inline __be32
+nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+{ return 0; }
+#endif
+
static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
{
/* As per referral draft: */
@@ -2012,6 +2083,9 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
int err;
int aclsupport = 0;
struct nfs4_acl *acl = NULL;
+ void *context = NULL;
+ int contextlen;
+ bool contextsupport = false;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
u32 minorversion = resp->cstate.minorversion;
struct path path = {
@@ -2065,6 +2139,21 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
}
}
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+ if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) ||
+ bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+ err = security_inode_getsecctx(dentry->d_inode,
+ &context, &contextlen);
+ contextsupport = (err == 0);
+ if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
+ if (err == -EOPNOTSUPP)
+ bmval2 &= ~FATTR4_WORD2_SECURITY_LABEL;
+ else if (err)
+ goto out_nfserr;
+ }
+ }
+#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
+
if (bmval2) {
if ((buflen -= 16) < 0)
goto out_resource;
@@ -2093,6 +2182,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
if (!aclsupport)
word0 &= ~FATTR4_WORD0_ACL;
+ if (!contextsupport)
+ word2 &= ~FATTR4_WORD2_SECURITY_LABEL;
if (!word2) {
if ((buflen -= 12) < 0)
goto out_resource;
@@ -2400,6 +2491,12 @@ out_acl:
get_parent_attributes(exp, &stat);
WRITE64(stat.ino);
}
+ if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
+ status = nfsd4_encode_security_label(rqstp, context,
+ contextlen, &p, &buflen);
+ if (status)
+ goto out;
+ }
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
WRITE32(3);
WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
@@ -2412,6 +2509,10 @@ out_acl:
status = nfs_ok;
out:
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+ if (context)
+ security_release_secctx(context, contextlen);
+#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
kfree(acl);
if (fhp == &tempfh)
fh_put(&tempfh);
@@ -3176,16 +3277,18 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
{
__be32 *p;
- RESERVE_SPACE(12);
+ RESERVE_SPACE(16);
if (nfserr) {
- WRITE32(2);
+ WRITE32(3);
+ WRITE32(0);
WRITE32(0);
WRITE32(0);
}
else {
- WRITE32(2);
+ WRITE32(3);
WRITE32(setattr->sa_bmval[0]);
WRITE32(setattr->sa_bmval[1]);
+ WRITE32(setattr->sa_bmval[2]);
}
ADJUST_ARGS();
return nfserr;
@@ -3226,6 +3329,14 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
return nfserr;
}
+static const u32 nfs4_minimal_spo_must_enforce[2] = {
+ [1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) |
+ 1 << (OP_EXCHANGE_ID - 32) |
+ 1 << (OP_CREATE_SESSION - 32) |
+ 1 << (OP_DESTROY_SESSION - 32) |
+ 1 << (OP_DESTROY_CLIENTID - 32)
+};
+
static __be32
nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_exchange_id *exid)
@@ -3264,6 +3375,20 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
/* state_protect4_r. Currently only support SP4_NONE */
BUG_ON(exid->spa_how != SP4_NONE);
WRITE32(exid->spa_how);
+ switch (exid->spa_how) {
+ case SP4_NONE:
+ break;
+ case SP4_MACH_CRED:
+ /* spo_must_enforce bitmap: */
+ WRITE32(2);
+ WRITE32(nfs4_minimal_spo_must_enforce[0]);
+ WRITE32(nfs4_minimal_spo_must_enforce[1]);
+ /* empty spo_must_allow bitmap: */
+ WRITE32(0);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
/* The server_owner struct */
WRITE64(minor_id); /* Minor id */
@@ -3635,13 +3760,17 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
BUG_ON(iov->iov_len > PAGE_SIZE);
if (nfsd4_has_session(cs)) {
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfs4_client *clp = cs->session->se_client;
if (cs->status != nfserr_replay_cache) {
nfsd4_store_cache_entry(resp);
cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
}
/* Renew the clientid on success and on replay */
- put_client_renew(cs->session->se_client);
+ spin_lock(&nn->client_lock);
nfsd4_put_session(cs->session);
+ spin_unlock(&nn->client_lock);
+ put_client_renew(clp);
}
return 1;
}
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index c0d9317..2bbd94e 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -24,7 +24,7 @@
/*
* nfsd version
*/
-#define NFSD_SUPPORTED_MINOR_VERSION 1
+#define NFSD_SUPPORTED_MINOR_VERSION 2
/*
* Maximum blocksizes supported by daemon under various circumstances.
*/
@@ -328,6 +328,13 @@ void nfsd_lockd_shutdown(void);
#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+ (NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL)
+#else
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0
+#endif
+
static inline u32 nfsd_suppattrs0(u32 minorversion)
{
return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
@@ -342,8 +349,11 @@ static inline u32 nfsd_suppattrs1(u32 minorversion)
static inline u32 nfsd_suppattrs2(u32 minorversion)
{
- return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2
- : NFSD4_SUPPORTED_ATTRS_WORD2;
+ switch (minorversion) {
+ default: return NFSD4_2_SUPPORTED_ATTRS_WORD2;
+ case 1: return NFSD4_1_SUPPORTED_ATTRS_WORD2;
+ case 0: return NFSD4_SUPPORTED_ATTRS_WORD2;
+ }
}
/* These will return ERR_INVAL if specified in GETATTR or READDIR. */
@@ -356,7 +366,11 @@ static inline u32 nfsd_suppattrs2(u32 minorversion)
#define NFSD_WRITEABLE_ATTRS_WORD1 \
(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \
| FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD_WRITEABLE_ATTRS_WORD2 FATTR4_WORD2_SECURITY_LABEL
+#else
#define NFSD_WRITEABLE_ATTRS_WORD2 0
+#endif
#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
NFSD_WRITEABLE_ATTRS_WORD0
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 262df5c..6b9f48c 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -116,7 +116,7 @@ struct svc_program nfsd_program = {
};
-u32 nfsd_supported_minorversion;
+u32 nfsd_supported_minorversion = 1;
int nfsd_vers(int vers, enum vers_op change)
{
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 274e2a1..424d8f5 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -246,6 +246,7 @@ struct nfs4_client {
nfs4_verifier cl_verifier; /* generated by client */
time_t cl_time; /* time of last lease renewal */
struct sockaddr_storage cl_addr; /* client ipaddress */
+ bool cl_mach_cred; /* SP4_MACH_CRED in force */
struct svc_cred cl_cred; /* setclientid principal */
clientid_t cl_clientid; /* generated by server */
nfs4_verifier cl_confirm; /* generated by server */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a6bc8a7..8ff6a00 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -28,6 +28,7 @@
#include <asm/uaccess.h>
#include <linux/exportfs.h>
#include <linux/writeback.h>
+#include <linux/security.h>
#ifdef CONFIG_NFSD_V3
#include "xdr3.h"
@@ -621,6 +622,33 @@ int nfsd4_is_junction(struct dentry *dentry)
return 0;
return 1;
}
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct xdr_netobj *label)
+{
+ __be32 error;
+ int host_error;
+ struct dentry *dentry;
+
+ error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
+ if (error)
+ return error;
+
+ dentry = fhp->fh_dentry;
+
+ mutex_lock(&dentry->d_inode->i_mutex);
+ host_error = security_inode_setsecctx(dentry, label->data, label->len);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ return nfserrno(host_error);
+}
+#else
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct xdr_netobj *label)
+{
+ return nfserr_notsupp;
+}
+#endif
+
#endif /* defined(CONFIG_NFSD_V4) */
#ifdef CONFIG_NFSD_V3
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 5b58941..a4be2e3 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -39,7 +39,6 @@
typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
/* nfsd/vfs.c */
-int fh_lock_parent(struct svc_fh *, struct dentry *);
int nfsd_racache_init(int);
void nfsd_racache_shutdown(void);
int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
@@ -56,6 +55,8 @@ int nfsd_mountpoint(struct dentry *, struct svc_export *);
__be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *,
struct nfs4_acl *);
int nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **);
+__be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *,
+ struct xdr_netobj *);
#endif /* CONFIG_NFSD_V4 */
__be32 nfsd_create(struct svc_rqst *, struct svc_fh *,
char *name, int len, struct iattr *attrs,
@@ -92,17 +93,13 @@ __be32 nfsd_remove(struct svc_rqst *,
struct svc_fh *, char *, int);
__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
char *name, int len);
-int nfsd_truncate(struct svc_rqst *, struct svc_fh *,
- unsigned long size);
__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *,
loff_t *, struct readdir_cd *, filldir_t);
__be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *,
struct kstatfs *, int access);
-int nfsd_notify_change(struct inode *, struct iattr *);
__be32 nfsd_permission(struct svc_rqst *, struct svc_export *,
struct dentry *, int);
-int nfsd_sync_dir(struct dentry *dp);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 3b271d2..b3ed644 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -40,6 +40,7 @@
#include "state.h"
#include "nfsd.h"
+#define NFSD4_MAX_SEC_LABEL_LEN 2048
#define NFSD4_MAX_TAGLEN 128
#define XDR_LEN(n) (((n) + 3) & ~3)
@@ -118,6 +119,7 @@ struct nfsd4_create {
struct iattr cr_iattr; /* request */
struct nfsd4_change_info cr_cinfo; /* response */
struct nfs4_acl *cr_acl;
+ struct xdr_netobj cr_label;
};
#define cr_linklen u.link.namelen
#define cr_linkname u.link.name
@@ -246,6 +248,7 @@ struct nfsd4_open {
struct nfs4_file *op_file; /* used during processing */
struct nfs4_ol_stateid *op_stp; /* used during processing */
struct nfs4_acl *op_acl;
+ struct xdr_netobj op_label;
};
#define op_iattr iattr
@@ -330,6 +333,7 @@ struct nfsd4_setattr {
u32 sa_bmval[3]; /* request */
struct iattr sa_iattr; /* request */
struct nfs4_acl *sa_acl;
+ struct xdr_netobj sa_label;
};
struct nfsd4_setclientid {
diff --git a/fs/select.c b/fs/select.c
index 6b14dc7..f9f49c4 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -28,6 +28,7 @@
#include <linux/hrtimer.h>
#include <linux/sched/rt.h>
#include <linux/freezer.h>
+#include <net/ll_poll.h>
#include <asm/uaccess.h>
@@ -386,9 +387,10 @@ get_max:
#define POLLEX_SET (POLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in,
- unsigned long out, unsigned long bit)
+ unsigned long out, unsigned long bit,
+ unsigned int ll_flag)
{
- wait->_key = POLLEX_SET;
+ wait->_key = POLLEX_SET | ll_flag;
if (in & bit)
wait->_key |= POLLIN_SET;
if (out & bit)
@@ -402,6 +404,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_table *wait;
int retval, i, timed_out = 0;
unsigned long slack = 0;
+ unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
+ unsigned long busy_end = 0;
rcu_read_lock();
retval = max_select_fd(n, fds);
@@ -424,6 +428,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
retval = 0;
for (;;) {
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
+ bool can_busy_loop = false;
inp = fds->in; outp = fds->out; exp = fds->ex;
rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
@@ -451,7 +456,8 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
f_op = f.file->f_op;
mask = DEFAULT_POLLMASK;
if (f_op && f_op->poll) {
- wait_key_set(wait, in, out, bit);
+ wait_key_set(wait, in, out,
+ bit, busy_flag);
mask = (*f_op->poll)(f.file, wait);
}
fdput(f);
@@ -470,6 +476,18 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
retval++;
wait->_qproc = NULL;
}
+ /* got something, stop busy polling */
+ if (retval) {
+ can_busy_loop = false;
+ busy_flag = 0;
+
+ /*
+ * only remember a returned
+ * POLL_BUSY_LOOP if we asked for it
+ */
+ } else if (busy_flag & mask)
+ can_busy_loop = true;
+
}
}
if (res_in)
@@ -488,6 +506,17 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
break;
}
+ /* only if found POLL_BUSY_LOOP sockets && not out of time */
+ if (can_busy_loop && !need_resched()) {
+ if (!busy_end) {
+ busy_end = busy_loop_end_time();
+ continue;
+ }
+ if (!busy_loop_timeout(busy_end))
+ continue;
+ }
+ busy_flag = 0;
+
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
@@ -719,7 +748,9 @@ struct poll_list {
* pwait poll_table will be used by the fd-provided poll handler for waiting,
* if pwait->_qproc is non-NULL.
*/
-static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
+static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
+ bool *can_busy_poll,
+ unsigned int busy_flag)
{
unsigned int mask;
int fd;
@@ -733,7 +764,10 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
mask = DEFAULT_POLLMASK;
if (f.file->f_op && f.file->f_op->poll) {
pwait->_key = pollfd->events|POLLERR|POLLHUP;
+ pwait->_key |= busy_flag;
mask = f.file->f_op->poll(f.file, pwait);
+ if (mask & busy_flag)
+ *can_busy_poll = true;
}
/* Mask out unneeded events. */
mask &= pollfd->events | POLLERR | POLLHUP;
@@ -752,6 +786,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
unsigned long slack = 0;
+ unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
+ unsigned long busy_end = 0;
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -764,6 +800,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
for (;;) {
struct poll_list *walk;
+ bool can_busy_loop = false;
for (walk = list; walk != NULL; walk = walk->next) {
struct pollfd * pfd, * pfd_end;
@@ -778,9 +815,13 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
* this. They'll get immediately deregistered
* when we break out and return.
*/
- if (do_pollfd(pfd, pt)) {
+ if (do_pollfd(pfd, pt, &can_busy_loop,
+ busy_flag)) {
count++;
pt->_qproc = NULL;
+ /* found something, stop busy polling */
+ busy_flag = 0;
+ can_busy_loop = false;
}
}
}
@@ -797,6 +838,17 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
if (count || timed_out)
break;
+ /* only if found POLL_BUSY_LOOP sockets && not out of time */
+ if (can_busy_loop && !need_resched()) {
+ if (!busy_end) {
+ busy_end = busy_loop_end_time();
+ continue;
+ }
+ if (!busy_loop_timeout(busy_end))
+ continue;
+ }
+ busy_flag = 0;
+
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
OpenPOWER on IntegriCloud