Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking changes from David Miller:
1) Get rid of the error prone NLA_PUT*() macros that used an embedded
goto.
2) Kill off the token-ring and MCA networking drivers, from Paul
Gortmaker.
3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
Eric Dumazet.
4) Add PTP hardware clock support to IGB and IXGBE, from Richard
Cochran and Jacob Keller.
5) Allow users to query timestamping capabilities of a card via
ethtool, from Richard Cochran.
6) Add loadbalance mode to the teaming driver, from Jiri Pirko. Part
of this is that we can now have BPF filters not attached to sockets,
and the loadbalancing function is calculated using one.
7) Francois Romieu went through the network drivers removing gratuitous
uses of netdev->base_addr, perhaps some day we can remove it
completely but it's used for ISA probing still.
8) Add a BPF JIT for sparc. I know, who cares, right? :-)
9) Move networking sysctl registry away from using the compatability
mode interfaces in the sysctl code. From Eric W Biederman.
10) Pavel Emelyanov added a way to save and restore TCP socket state via
TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
well as a way to forcefully bind a socket to a port via the
sk->sk_reuse value SK_FORCE_REUSE. There is also a
TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
enabled on the connection.
11) Several enhancements from Eric Dumazet that, in particular, can
enhance splice performance on TCP sockets significantly.
a) Reset the offset of the per-socket sendmsg page when we know
we're the only use of the page in linear_to_page().
b) Add facilities such that skb->data can be backed a page rather
than SLAB kmalloc'd memory. In particular devices which were
receiving into linear RX buffers can now end up providing paged
data.
The big result is that code like splice and GRO do not have to copy
any more.
12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
What can happen at high rates is that the sender hasn't grown his
receive buffer limits at all (he's not receiving data so really
doesn't need to), but the non-data ACKs consume receive buffer
space.
sk_add_backlog() is too aggressive in dropping frames in this case,
so relax it's requirements by using the receive buffer plus the send
buffer limit as the backlog limit instead of just the former.
Also from Eric Dumazet.
13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
Chris Elston.
14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
Basically, we can start fast retransmit before hiting the dupack
threshold under certain conditions.
15) New CODEL active queue management packet scheduler, from Eric
Dumazet based upon initial work by Dave Taht.
Basically, the big feature is that packets are dropped (or ECN bits
are set) based upon how long packets live in the queue, rather than
the queue length (which is what RED uses).
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
drivers/net/stmmac: seq_file fix memory leak
ipv6/exthdrs: strict Pad1 and PadN check
USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
USB: qmi_wwan: Make forced int 4 whitelist generic
net/ipv4: replace simple_strtoul with kstrtoul
net/ipv4/ipconfig: neaten __setup placement
net: qmi_wwan: Add Vodafone/Huawei K5005 support
net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
ipv6: use skb coalescing in reassembly
ipv4: use skb coalescing in defragmentation
net: introduce skb_try_coalesce()
net:ipv6:fixed space issues relating to operators.
net:ipv6:fixed a trailing white space issue.
ipv6: disable GSO on sockets hitting dst_allfrag
tg3: use netdev_alloc_frag() API
net: napi_frags_skb() is static
ppp: avoid false drop_monitor false positives
ipv6: bool/const conversions phase2
ipx: Remove spurious NULL checking in ipx_ioctl().
...
diff --git a/arch/x86/include/asm/stat.h b/arch/x86/include/asm/stat.h
index e0b1d9b..7b3ddc3 100644
--- a/arch/x86/include/asm/stat.h
+++ b/arch/x86/include/asm/stat.h
@@ -25,6 +25,12 @@
unsigned long __unused5;
};
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT_PADDING(st) do { \
+ st.__unused4 = 0; \
+ st.__unused5 = 0; \
+} while (0)
+
#define STAT64_HAS_BROKEN_ST_INO 1
/* This matches struct stat64 in glibc2.1, hence the absolutely
@@ -63,6 +69,12 @@
unsigned long long st_ino;
};
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT64_PADDING(st) do { \
+ memset(&st.__pad0, 0, sizeof(st.__pad0)); \
+ memset(&st.__pad3, 0, sizeof(st.__pad3)); \
+} while (0)
+
#else /* __i386__ */
struct stat {
@@ -87,6 +99,15 @@
unsigned long st_ctime_nsec;
long __unused[3];
};
+
+/* We don't need to memset the whole thing just to initialize the padding */
+#define INIT_STRUCT_STAT_PADDING(st) do { \
+ st.__pad0 = 0; \
+ st.__unused[0] = 0; \
+ st.__unused[1] = 0; \
+ st.__unused[2] = 0; \
+} while (0)
+
#endif
/* for 32bit emulation and 32 bit kernels */
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index d6ae30b..2e4e4b0 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -44,13 +44,6 @@
}
EXPORT_SYMBOL_GPL(copy_from_user_nmi);
-static inline unsigned long count_bytes(unsigned long mask)
-{
- mask = (mask - 1) & ~mask;
- mask >>= 7;
- return count_masked_bytes(mask);
-}
-
/*
* Do a strncpy, return length of string without final '\0'.
* 'count' is the user-supplied count (return 'count' if we
@@ -69,16 +62,19 @@
max = count;
while (max >= sizeof(unsigned long)) {
- unsigned long c;
+ unsigned long c, mask;
/* Fall back to byte-at-a-time if we get a page fault */
if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
break;
- /* This can write a few bytes past the NUL character, but that's ok */
+ mask = has_zero(c);
+ if (mask) {
+ mask = (mask - 1) & ~mask;
+ mask >>= 7;
+ *(unsigned long *)(dst+res) = c & mask;
+ return res + count_masked_bytes(mask);
+ }
*(unsigned long *)(dst+res) = c;
- c = has_zero(c);
- if (c)
- return res + count_bytes(c);
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
diff --git a/fs/dcache.c b/fs/dcache.c
index b80531c..92099f6 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -153,16 +153,12 @@
* In contrast, 'ct' and 'tcount' can be from a pathname, and do
* need the careful unaligned handling.
*/
-static inline int dentry_cmp(const unsigned char *cs, size_t scount,
- const unsigned char *ct, size_t tcount)
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
unsigned long a,b,mask;
- if (unlikely(scount != tcount))
- return 1;
-
for (;;) {
- a = load_unaligned_zeropad(cs);
+ a = *(unsigned long *)cs;
b = load_unaligned_zeropad(ct);
if (tcount < sizeof(unsigned long))
break;
@@ -180,12 +176,8 @@
#else
-static inline int dentry_cmp(const unsigned char *cs, size_t scount,
- const unsigned char *ct, size_t tcount)
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
- if (scount != tcount)
- return 1;
-
do {
if (*cs != *ct)
return 1;
@@ -198,6 +190,27 @@
#endif
+static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
+{
+ /*
+ * Be careful about RCU walk racing with rename:
+ * use ACCESS_ONCE to fetch the name pointer.
+ *
+ * NOTE! Even if a rename will mean that the length
+ * was not loaded atomically, we don't care. The
+ * RCU walk will check the sequence count eventually,
+ * and catch it. And we won't overrun the buffer,
+ * because we're reading the name pointer atomically,
+ * and a dentry name is guaranteed to be properly
+ * terminated with a NUL byte.
+ *
+ * End result: even if 'len' is wrong, we'll exit
+ * early because the data cannot match (there can
+ * be no NUL in the ct/tcount data)
+ */
+ return dentry_string_cmp(ACCESS_ONCE(dentry->d_name.name), ct, tcount);
+}
+
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
@@ -1439,18 +1452,18 @@
}
list_for_each_entry(alias, &inode->i_dentry, d_alias) {
- struct qstr *qstr = &alias->d_name;
-
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
* parent changes, because the parent inode i_mutex is held.
*/
- if (qstr->hash != hash)
+ if (alias->d_name.hash != hash)
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (dentry_cmp(qstr->name, qstr->len, name, len))
+ if (alias->d_name.len != len)
+ continue;
+ if (dentry_cmp(alias, name, len))
continue;
__dget(alias);
return alias;
@@ -1489,7 +1502,7 @@
struct dentry *res = NULL;
if (root_inode) {
- static const struct qstr name = { .name = "/", .len = 1 };
+ static const struct qstr name = QSTR_INIT("/", 1);
res = __d_alloc(root_inode->i_sb, &name);
if (res)
@@ -1727,6 +1740,48 @@
}
EXPORT_SYMBOL(d_add_ci);
+/*
+ * Do the slow-case of the dentry name compare.
+ *
+ * Unlike the dentry_cmp() function, we need to atomically
+ * load the name, length and inode information, so that the
+ * filesystem can rely on them, and can use the 'name' and
+ * 'len' information without worrying about walking off the
+ * end of memory etc.
+ *
+ * Thus the read_seqcount_retry() and the "duplicate" info
+ * in arguments (the low-level filesystem should not look
+ * at the dentry inode or name contents directly, since
+ * rename can change them while we're in RCU mode).
+ */
+enum slow_d_compare {
+ D_COMP_OK,
+ D_COMP_NOMATCH,
+ D_COMP_SEQRETRY,
+};
+
+static noinline enum slow_d_compare slow_dentry_cmp(
+ const struct dentry *parent,
+ struct inode *inode,
+ struct dentry *dentry,
+ unsigned int seq,
+ const struct qstr *name)
+{
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ struct inode *i = dentry->d_inode;
+
+ if (read_seqcount_retry(&dentry->d_seq, seq)) {
+ cpu_relax();
+ return D_COMP_SEQRETRY;
+ }
+ if (parent->d_op->d_compare(parent, inode,
+ dentry, i,
+ tlen, tname, name))
+ return D_COMP_NOMATCH;
+ return D_COMP_OK;
+}
+
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
@@ -1753,15 +1808,17 @@
* the returned dentry, so long as its parent's seqlock is checked after the
* child is looked up. Thus, an interlocking stepping of sequence lock checks
* is formed, giving integrity down the path walk.
+ *
+ * NOTE! The caller *has* to check the resulting dentry against the sequence
+ * number we've returned before using any of the resulting dentry state!
*/
struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
- unsigned *seqp, struct inode **inode)
+ unsigned *seqp, struct inode *inode)
{
- unsigned int len = name->len;
- unsigned int hash = name->hash;
+ u64 hashlen = name->hash_len;
const unsigned char *str = name->name;
- struct hlist_bl_head *b = d_hash(parent, hash);
+ struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen));
struct hlist_bl_node *node;
struct dentry *dentry;
@@ -1787,49 +1844,45 @@
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
unsigned seq;
- struct inode *i;
- const char *tname;
- int tlen;
-
- if (dentry->d_name.hash != hash)
- continue;
seqretry:
- seq = read_seqcount_begin(&dentry->d_seq);
+ /*
+ * The dentry sequence count protects us from concurrent
+ * renames, and thus protects inode, parent and name fields.
+ *
+ * The caller must perform a seqcount check in order
+ * to do anything useful with the returned dentry,
+ * including using the 'd_inode' pointer.
+ *
+ * NOTE! We do a "raw" seqcount_begin here. That means that
+ * we don't wait for the sequence count to stabilize if it
+ * is in the middle of a sequence change. If we do the slow
+ * dentry compare, we will do seqretries until it is stable,
+ * and if we end up with a successful lookup, we actually
+ * want to exit RCU lookup anyway.
+ */
+ seq = raw_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
- if (d_unhashed(dentry))
- continue;
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
- i = dentry->d_inode;
- prefetch(tname);
- /*
- * This seqcount check is required to ensure name and
- * len are loaded atomically, so as not to walk off the
- * edge of memory when walking. If we could load this
- * atomically some other way, we could drop this check.
- */
- if (read_seqcount_retry(&dentry->d_seq, seq))
- goto seqretry;
- if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
- if (parent->d_op->d_compare(parent, *inode,
- dentry, i,
- tlen, tname, name))
- continue;
- } else {
- if (dentry_cmp(tname, tlen, str, len))
- continue;
- }
- /*
- * No extra seqcount check is required after the name
- * compare. The caller must perform a seqcount check in
- * order to do anything useful with the returned dentry
- * anyway.
- */
*seqp = seq;
- *inode = i;
- return dentry;
+
+ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
+ if (dentry->d_name.hash != hashlen_hash(hashlen))
+ continue;
+ switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) {
+ case D_COMP_OK:
+ return dentry;
+ case D_COMP_NOMATCH:
+ continue;
+ default:
+ goto seqretry;
+ }
+ }
+
+ if (dentry->d_name.hash_len != hashlen)
+ continue;
+ if (!dentry_cmp(dentry, str, hashlen_len(hashlen)))
+ return dentry;
}
return NULL;
}
@@ -1908,8 +1961,6 @@
rcu_read_lock();
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- const char *tname;
- int tlen;
if (dentry->d_name.hash != hash)
continue;
@@ -1924,15 +1975,17 @@
* It is safe to compare names since d_move() cannot
* change the qstr (protected by d_lock).
*/
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
if (parent->d_op->d_compare(parent, parent->d_inode,
dentry, dentry->d_inode,
tlen, tname, name))
goto next;
} else {
- if (dentry_cmp(tname, tlen, str, len))
+ if (dentry->d_name.len != len)
+ goto next;
+ if (dentry_cmp(dentry, str, len))
goto next;
}
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index dffb865..f663a67 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -79,7 +79,7 @@
struct dentry *ext2_get_parent(struct dentry *child)
{
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index d7940b2..eeb63df 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1045,7 +1045,7 @@
struct dentry *ext3_get_parent(struct dentry *child)
{
unsigned long ino;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct ext3_dir_entry_2 * de;
struct buffer_head *bh;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 349d7b3..e2a3f4b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1052,10 +1052,7 @@
struct dentry *ext4_get_parent(struct dentry *child)
{
__u32 ino;
- static const struct qstr dotdot = {
- .name = "..",
- .len = 2,
- };
+ static const struct qstr dotdot = QSTR_INIT("..", 2);
struct ext4_dir_entry_2 * de;
struct buffer_head *bh;
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index a836056..8aaeb07 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -821,7 +821,7 @@
struct buffer_head *bh;
struct gfs2_leaf *leaf;
struct gfs2_dirent *dent;
- struct qstr name = { .name = "", .len = 0, .hash = 0 };
+ struct qstr name = { .name = "" };
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
diff --git a/fs/libfs.c b/fs/libfs.c
index 18d08f5..f86ec27 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -68,7 +68,7 @@
int dcache_dir_open(struct inode *inode, struct file *file)
{
- static struct qstr cursor_name = {.len = 1, .name = "."};
+ static struct qstr cursor_name = QSTR_INIT(".", 1);
file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
@@ -225,7 +225,7 @@
struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
struct dentry *dentry;
struct inode *root;
- struct qstr d_name = {.name = name, .len = strlen(name)};
+ struct qstr d_name = QSTR_INIT(name, strlen(name));
if (IS_ERR(s))
return ERR_CAST(s);
diff --git a/fs/namei.c b/fs/namei.c
index c427919..f9e883c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -116,47 +116,37 @@
* POSIX.1 2.4: an empty pathname is invalid (ENOENT).
* PATH_MAX includes the nul terminator --RR.
*/
-static int do_getname(const char __user *filename, char *page)
-{
- int retval;
- unsigned long len = PATH_MAX;
-
- if (!segment_eq(get_fs(), KERNEL_DS)) {
- if ((unsigned long) filename >= TASK_SIZE)
- return -EFAULT;
- if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
- len = TASK_SIZE - (unsigned long) filename;
- }
-
- retval = strncpy_from_user(page, filename, len);
- if (retval > 0) {
- if (retval < len)
- return 0;
- return -ENAMETOOLONG;
- } else if (!retval)
- retval = -ENOENT;
- return retval;
-}
-
static char *getname_flags(const char __user *filename, int flags, int *empty)
{
- char *result = __getname();
- int retval;
+ char *result = __getname(), *err;
+ int len;
- if (!result)
+ if (unlikely(!result))
return ERR_PTR(-ENOMEM);
- retval = do_getname(filename, result);
- if (retval < 0) {
- if (retval == -ENOENT && empty)
+ len = strncpy_from_user(result, filename, PATH_MAX);
+ err = ERR_PTR(len);
+ if (unlikely(len < 0))
+ goto error;
+
+ /* The empty path is special. */
+ if (unlikely(!len)) {
+ if (empty)
*empty = 1;
- if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
- __putname(result);
- return ERR_PTR(retval);
- }
+ err = ERR_PTR(-ENOENT);
+ if (!(flags & LOOKUP_EMPTY))
+ goto error;
}
- audit_getname(result);
- return result;
+
+ err = ERR_PTR(-ENAMETOOLONG);
+ if (likely(len < PATH_MAX)) {
+ audit_getname(result);
+ return result;
+ }
+
+error:
+ __putname(result);
+ return err;
}
char *getname(const char __user * filename)
@@ -1154,12 +1144,25 @@
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
- *inode = nd->inode;
- dentry = __d_lookup_rcu(parent, name, &seq, inode);
+ dentry = __d_lookup_rcu(parent, name, &seq, nd->inode);
if (!dentry)
goto unlazy;
- /* Memory barrier in read_seqcount_begin of child is enough */
+ /*
+ * This sequence count validates that the inode matches
+ * the dentry name information from lookup.
+ */
+ *inode = dentry->d_inode;
+ if (read_seqcount_retry(&dentry->d_seq, seq))
+ return -ECHILD;
+
+ /*
+ * This sequence count validates that the parent had no
+ * changes while we did the lookup of the dentry above.
+ *
+ * The memory barrier in read_seqcount_begin of child is
+ * enough, we can use __read_seqcount_retry here.
+ */
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
nd->seq = seq;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8789210..eedd24d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -477,10 +477,7 @@
static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
- struct qstr filename = {
- .len = entry->len,
- .name = entry->name,
- };
+ struct qstr filename = QSTR_INIT(entry->name, entry->len);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = parent->d_inode;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 5242eae..75c6829 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -398,8 +398,7 @@
{
struct nfs_removeargs arg = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
};
struct nfs_removeres res;
struct rpc_message msg = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 99650aa..ab985f6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2782,8 +2782,7 @@
struct nfs_server *server = NFS_SERVER(dir);
struct nfs_removeargs args = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
.bitmask = server->attr_bitmask,
};
struct nfs_removeres res = {
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b63b6f4..d6408b6 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -335,8 +335,7 @@
{
struct nfs_removeargs arg = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
};
struct rpc_message msg = {
.rpc_proc = &nfs_procedures[NFSPROC_REMOVE],
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index fce2bbe..0bb2c20 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -441,7 +441,7 @@
{
unsigned long ino;
struct inode *inode;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct nilfs_root *root;
ino = nilfs_inode_by_name(child->d_inode, &dotdot);
diff --git a/fs/stat.c b/fs/stat.c
index c733dc5..0cef336 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -57,12 +57,13 @@
int vfs_fstat(unsigned int fd, struct kstat *stat)
{
- struct file *f = fget(fd);
+ int fput_needed;
+ struct file *f = fget_light(fd, &fput_needed);
int error = -EBADF;
if (f) {
error = vfs_getattr(f->f_path.mnt, f->f_path.dentry, stat);
- fput(f);
+ fput_light(f, fput_needed);
}
return error;
}
@@ -190,24 +191,32 @@
#endif /* __ARCH_WANT_OLD_STAT */
+#if BITS_PER_LONG == 32
+# define choose_32_64(a,b) a
+#else
+# define choose_32_64(a,b) b
+#endif
+
+#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x)
+#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x)
+
+#ifndef INIT_STRUCT_STAT_PADDING
+# define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
+#endif
+
static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
{
struct stat tmp;
-#if BITS_PER_LONG == 32
- if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+ if (!valid_dev(stat->dev) || !valid_dev(stat->rdev))
return -EOVERFLOW;
-#else
- if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
+#if BITS_PER_LONG == 32
+ if (stat->size > MAX_NON_LFS)
return -EOVERFLOW;
#endif
- memset(&tmp, 0, sizeof(tmp));
-#if BITS_PER_LONG == 32
- tmp.st_dev = old_encode_dev(stat->dev);
-#else
- tmp.st_dev = new_encode_dev(stat->dev);
-#endif
+ INIT_STRUCT_STAT_PADDING(tmp);
+ tmp.st_dev = encode_dev(stat->dev);
tmp.st_ino = stat->ino;
if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
@@ -217,15 +226,7 @@
return -EOVERFLOW;
SET_UID(tmp.st_uid, stat->uid);
SET_GID(tmp.st_gid, stat->gid);
-#if BITS_PER_LONG == 32
- tmp.st_rdev = old_encode_dev(stat->rdev);
-#else
- tmp.st_rdev = new_encode_dev(stat->rdev);
-#endif
-#if BITS_PER_LONG == 32
- if (stat->size > MAX_NON_LFS)
- return -EOVERFLOW;
-#endif
+ tmp.st_rdev = encode_dev(stat->rdev);
tmp.st_size = stat->size;
tmp.st_atime = stat->atime.tv_sec;
tmp.st_mtime = stat->mtime.tv_sec;
@@ -327,11 +328,15 @@
/* ---------- LFS-64 ----------- */
#ifdef __ARCH_WANT_STAT64
+#ifndef INIT_STRUCT_STAT64_PADDING
+# define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st))
+#endif
+
static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf)
{
struct stat64 tmp;
- memset(&tmp, 0, sizeof(struct stat64));
+ INIT_STRUCT_STAT64_PADDING(tmp);
#ifdef CONFIG_MIPS
/* mips has weird padding, so we don't get 64 bits there */
if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev))
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 16ad84d..abd5133 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2361,7 +2361,7 @@
* by passing 'ubifs_tnc_remove_nm()' the same key but
* an unmatchable name.
*/
- struct qstr noname = { .len = 0, .name = "" };
+ struct qstr noname = { .name = "" };
err = dbg_check_tnc(c, 0);
mutex_unlock(&c->tnc_mutex);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 85b2722..7a8bafa 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -298,7 +298,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
int err, type;
@@ -361,7 +361,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_inode *ui;
struct ubifs_dent_node *xent;
union ubifs_key key;
@@ -524,7 +524,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
int err;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 38de8f2..a165c66 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1193,7 +1193,7 @@
{
struct kernel_lb_addr tloc;
struct inode *inode = NULL;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct fileIdentDesc cfi;
struct udf_fileident_bh fibh;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index ac8e279..302f340 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -146,10 +146,7 @@
static struct dentry *ufs_get_parent(struct dentry *child)
{
- struct qstr dot_dot = {
- .name = "..",
- .len = 2,
- };
+ struct qstr dot_dot = QSTR_INIT("..", 2);
ino_t ino;
ino = ufs_inode_by_name(child->d_inode, &dot_dot);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 7e11f14..094789f 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -25,6 +25,13 @@
#define IS_ROOT(x) ((x) == (x)->d_parent)
+/* The hash is always the low bits of hash_len */
+#ifdef __LITTLE_ENDIAN
+ #define HASH_LEN_DECLARE u32 hash; u32 len;
+#else
+ #define HASH_LEN_DECLARE u32 len; u32 hash;
+#endif
+
/*
* "quick string" -- eases parameter passing, but more importantly
* saves "metadata" about the string (ie length and the hash).
@@ -33,11 +40,19 @@
* dentry.
*/
struct qstr {
- unsigned int hash;
- unsigned int len;
+ union {
+ struct {
+ HASH_LEN_DECLARE;
+ };
+ u64 hash_len;
+ };
const unsigned char *name;
};
+#define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
+#define hashlen_hash(hashlen) ((u32) (hashlen))
+#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
+
struct dentry_stat_t {
int nr_dentry;
int nr_unused;
@@ -282,7 +297,7 @@
extern struct dentry *__d_lookup(struct dentry *, struct qstr *);
extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
- unsigned *seq, struct inode **inode);
+ unsigned *seq, struct inode *inode);
/**
* __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74aa71b..7d5c37f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -896,10 +896,8 @@
unsigned long size);
void zap_page_range(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *);
-void unmap_vmas(struct mmu_gather *tlb,
- struct vm_area_struct *start_vma, unsigned long start_addr,
- unsigned long end_addr, unsigned long *nr_accounted,
- struct zap_details *);
+void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
+ unsigned long start, unsigned long end);
/**
* mm_walk - callbacks for walk_page_range
diff --git a/mm/memory.c b/mm/memory.c
index 6105f47..1e77da6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1295,7 +1295,7 @@
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
- unsigned long end_addr, unsigned long *nr_accounted,
+ unsigned long end_addr,
struct zap_details *details)
{
unsigned long start = max(vma->vm_start, start_addr);
@@ -1307,9 +1307,6 @@
if (end <= vma->vm_start)
return;
- if (vma->vm_flags & VM_ACCOUNT)
- *nr_accounted += (end - start) >> PAGE_SHIFT;
-
if (unlikely(is_pfn_mapping(vma)))
untrack_pfn_vma(vma, 0, 0);
@@ -1339,8 +1336,6 @@
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
- * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
- * @details: details of nonlinear truncation or shared cache invalidation
*
* Unmap all pages in the vma list.
*
@@ -1355,15 +1350,13 @@
*/
void unmap_vmas(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
- unsigned long end_addr, unsigned long *nr_accounted,
- struct zap_details *details)
+ unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
- unmap_single_vma(tlb, vma, start_addr, end_addr, nr_accounted,
- details);
+ unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
}
@@ -1376,19 +1369,21 @@
*
* Caller must protect the VMA list
*/
-void zap_page_range(struct vm_area_struct *vma, unsigned long address,
+void zap_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
- unsigned long end = address + size;
- unsigned long nr_accounted = 0;
+ unsigned long end = start + size;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, 0);
update_hiwater_rss(mm);
- unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
- tlb_finish_mmu(&tlb, address, end);
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
+ unmap_single_vma(&tlb, vma, start, end, details);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
}
/**
@@ -1406,13 +1401,12 @@
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
unsigned long end = address + size;
- unsigned long nr_accounted = 0;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, 0);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, address, end);
- unmap_single_vma(&tlb, vma, address, end, &nr_accounted, details);
+ unmap_single_vma(&tlb, vma, address, end, details);
mmu_notifier_invalidate_range_end(mm, address, end);
tlb_finish_mmu(&tlb, address, end);
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 848ef52..69a1889 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1889,15 +1889,20 @@
*/
static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
{
+ unsigned long nr_accounted = 0;
+
/* Update high watermark before we lower total_vm */
update_hiwater_vm(mm);
do {
long nrpages = vma_pages(vma);
+ if (vma->vm_flags & VM_ACCOUNT)
+ nr_accounted += nrpages;
mm->total_vm -= nrpages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
vma = remove_vma(vma);
} while (vma);
+ vm_unacct_memory(nr_accounted);
validate_mm(mm);
}
@@ -1912,13 +1917,11 @@
{
struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
struct mmu_gather tlb;
- unsigned long nr_accounted = 0;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, 0);
update_hiwater_rss(mm);
- unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
- vm_unacct_memory(nr_accounted);
+ unmap_vmas(&tlb, vma, start, end);
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
next ? next->vm_start : 0);
tlb_finish_mmu(&tlb, start, end);
@@ -2305,8 +2308,7 @@
tlb_gather_mmu(&tlb, mm, 1);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
- unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
- vm_unacct_memory(nr_accounted);
+ unmap_vmas(&tlb, vma, 0, -1);
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(&tlb, 0, -1);
@@ -2315,8 +2317,12 @@
* Walk the list again, actually closing and freeing it,
* with preemption enabled, without holding any MM locks.
*/
- while (vma)
+ while (vma) {
+ if (vma->vm_flags & VM_ACCOUNT)
+ nr_accounted += vma_pages(vma);
vma = remove_vma(vma);
+ }
+ vm_unacct_memory(nr_accounted);
BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index adf2990..7fee13b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -127,9 +127,7 @@
{
static uint32_t clntid;
char name[15];
- struct qstr q = {
- .name = name,
- };
+ struct qstr q = { .name = name };
struct dentry *dir, *dentry;
int error;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 3b62cf2..fd24239 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1059,12 +1059,9 @@
struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
const unsigned char *dir_name)
{
- struct qstr dir = {
- .name = dir_name,
- .len = strlen(dir_name),
- .hash = full_name_hash(dir_name, strlen(dir_name)),
- };
+ struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name));
+ dir.hash = full_name_hash(dir.name, dir.len);
return d_lookup(sb->s_root, &dir);
}
EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);
