summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-01-21 12:32:08 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-21 12:32:08 -0800
commiteae21770b4fed5597623aad0d618190fa60426ff (patch)
tree23c59fb7a33e93a79525e2b10d56df54d40049d1 /fs
parente9f57ebcba563e0cd532926cab83c92bb4d79360 (diff)
parent9f273c24ec5f4a6f785bb83e931b3808a07b459e (diff)
Merge branch 'akpm' (patches from Andrew)
Merge third patch-bomb from Andrew Morton: "I'm pretty much done for -rc1 now: - the rest of MM, basically - lib/ updates - checkpatch, epoll, hfs, fatfs, ptrace, coredump, exit - cpu_mask simplifications - kexec, rapidio, MAINTAINERS etc, etc. - more dma-mapping cleanups/simplifications from hch" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (109 commits) MAINTAINERS: add/fix git URLs for various subsystems mm: memcontrol: add "sock" to cgroup2 memory.stat mm: memcontrol: basic memory statistics in cgroup2 memory controller mm: memcontrol: do not uncharge old page in page cache replacement Documentation: cgroup: add memory.swap.{current,max} description mm: free swap cache aggressively if memcg swap is full mm: vmscan: do not scan anon pages if memcg swap limit is hit swap.h: move memcg related stuff to the end of the file mm: memcontrol: replace mem_cgroup_lruvec_online with mem_cgroup_online mm: vmscan: pass memcg to get_scan_count() mm: memcontrol: charge swap to cgroup2 mm: memcontrol: clean up alloc, online, offline, free functions mm: memcontrol: flatten struct cg_proto mm: memcontrol: rein in the CONFIG space madness net: drop tcp_memcontrol.c mm: memcontrol: introduce CONFIG_MEMCG_LEGACY_KMEM mm: memcontrol: allow to disable kmem accounting for cgroup2 mm: memcontrol: account "kmem" consumers in cgroup2 memory controller mm: memcontrol: move kmem accounting code to CONFIG_MEMCG mm: memcontrol: separate kmem code from legacy tcp accounting code ...
Diffstat (limited to 'fs')
-rw-r--r--fs/adfs/adfs.h28
-rw-r--r--fs/coredump.c20
-rw-r--r--fs/eventpoll.c24
-rw-r--r--fs/fat/cache.c79
-rw-r--r--fs/fat/dir.c2
-rw-r--r--fs/fat/fat.h8
-rw-r--r--fs/fat/fatent.c24
-rw-r--r--fs/fat/file.c61
-rw-r--r--fs/fat/inode.c104
-rw-r--r--fs/hfs/catalog.c6
-rw-r--r--fs/overlayfs/super.c1
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c34
-rw-r--r--fs/proc/namespaces.c4
-rw-r--r--fs/proc/task_mmu.c2
15 files changed, 313 insertions, 86 deletions
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index ea4aba56f29d..fadf408bdd46 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -44,24 +44,24 @@ struct adfs_dir_ops;
*/
struct adfs_sb_info {
union { struct {
- struct adfs_discmap *s_map; /* bh list containing map */
- const struct adfs_dir_ops *s_dir; /* directory operations */
+ struct adfs_discmap *s_map; /* bh list containing map */
+ const struct adfs_dir_ops *s_dir; /* directory operations */
};
- struct rcu_head rcu; /* used only at shutdown time */
+ struct rcu_head rcu; /* used only at shutdown time */
};
- kuid_t s_uid; /* owner uid */
- kgid_t s_gid; /* owner gid */
- umode_t s_owner_mask; /* ADFS owner perm -> unix perm */
- umode_t s_other_mask; /* ADFS other perm -> unix perm */
+ kuid_t s_uid; /* owner uid */
+ kgid_t s_gid; /* owner gid */
+ umode_t s_owner_mask; /* ADFS owner perm -> unix perm */
+ umode_t s_other_mask; /* ADFS other perm -> unix perm */
int s_ftsuffix; /* ,xyz hex filetype suffix option */
- __u32 s_ids_per_zone; /* max. no ids in one zone */
- __u32 s_idlen; /* length of ID in map */
- __u32 s_map_size; /* sector size of a map */
- unsigned long s_size; /* total size (in blocks) of this fs */
- signed int s_map2blk; /* shift left by this for map->sector */
- unsigned int s_log2sharesize;/* log2 share size */
- __le32 s_version; /* disc format version */
+ __u32 s_ids_per_zone; /* max. no ids in one zone */
+ __u32 s_idlen; /* length of ID in map */
+ __u32 s_map_size; /* sector size of a map */
+ unsigned long s_size; /* total size (in blocks) of this fs */
+ signed int s_map2blk; /* shift left by this for map->sector*/
+ unsigned int s_log2sharesize;/* log2 share size */
+ __le32 s_version; /* disc format version */
unsigned int s_namelen; /* maximum number of characters in name */
};
diff --git a/fs/coredump.c b/fs/coredump.c
index b3c153ca435d..9ea87e9fdccf 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -118,6 +118,26 @@ int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
ret = cn_vprintf(cn, fmt, arg);
va_end(arg);
+ if (ret == 0) {
+ /*
+ * Ensure that this coredump name component can't cause the
+ * resulting corefile path to consist of a ".." or ".".
+ */
+ if ((cn->used - cur == 1 && cn->corename[cur] == '.') ||
+ (cn->used - cur == 2 && cn->corename[cur] == '.'
+ && cn->corename[cur+1] == '.'))
+ cn->corename[cur] = '!';
+
+ /*
+ * Empty names are fishy and could be used to create a "//" in a
+ * corefile name, causing the coredump to happen one directory
+ * level too high. Enforce that all components of the core
+ * pattern are at least one character long.
+ */
+ if (cn->used == cur)
+ ret = cn_printf(cn, "!");
+ }
+
for (; cur < cn->used; ++cur) {
if (cn->corename[cur] == '/')
cn->corename[cur] = '!';
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..ae1dbcf47e97 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -92,7 +92,7 @@
*/
/* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
@@ -1002,6 +1002,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
unsigned long flags;
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
+ int ewake = 0;
if ((unsigned long)key & POLLFREE) {
ep_pwq_from_wait(wait)->whead = NULL;
@@ -1066,8 +1067,10 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
- if (waitqueue_active(&ep->wq))
+ if (waitqueue_active(&ep->wq)) {
+ ewake = 1;
wake_up_locked(&ep->wq);
+ }
if (waitqueue_active(&ep->poll_wait))
pwake++;
@@ -1078,6 +1081,9 @@ out_unlock:
if (pwake)
ep_poll_safewake(&ep->poll_wait);
+ if (epi->event.events & EPOLLEXCLUSIVE)
+ return ewake;
+
return 1;
}
@@ -1095,7 +1101,10 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
- add_wait_queue(whead, &pwq->wait);
+ if (epi->event.events & EPOLLEXCLUSIVE)
+ add_wait_queue_exclusive(whead, &pwq->wait);
+ else
+ add_wait_queue(whead, &pwq->wait);
list_add_tail(&pwq->llink, &epi->pwqlist);
epi->nwait++;
} else {
@@ -1862,6 +1871,15 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
goto error_tgt_fput;
/*
+ * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
+ * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
+ * Also, we do not currently supported nested exclusive wakeups.
+ */
+ if ((epds.events & EPOLLEXCLUSIVE) && (op == EPOLL_CTL_MOD ||
+ (op == EPOLL_CTL_ADD && is_file_epoll(tf.file))))
+ goto error_tgt_fput;
+
+ /*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 93fc62232ec2..5d384921524d 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -301,15 +301,59 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
return dclus;
}
-int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
- unsigned long *mapped_blocks, int create)
+int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+ sector_t last_block,
+ unsigned long *mapped_blocks, sector_t *bmap)
{
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ int cluster, offset;
+
+ cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+ offset = sector & (sbi->sec_per_clus - 1);
+ cluster = fat_bmap_cluster(inode, cluster);
+ if (cluster < 0)
+ return cluster;
+ else if (cluster) {
+ *bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+ *mapped_blocks = sbi->sec_per_clus - offset;
+ if (*mapped_blocks > last_block - sector)
+ *mapped_blocks = last_block - sector;
+ }
+
+ return 0;
+}
+
+static int is_exceed_eof(struct inode *inode, sector_t sector,
+ sector_t *last_block, int create)
+{
+ struct super_block *sb = inode->i_sb;
const unsigned long blocksize = sb->s_blocksize;
const unsigned char blocksize_bits = sb->s_blocksize_bits;
+
+ *last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
+ if (sector >= *last_block) {
+ if (!create)
+ return 1;
+
+ /*
+ * ->mmu_private can access on only allocation path.
+ * (caller must hold ->i_mutex)
+ */
+ *last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+ >> blocksize_bits;
+ if (sector >= *last_block)
+ return 1;
+ }
+
+ return 0;
+}
+
+int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
+ unsigned long *mapped_blocks, int create, bool from_bmap)
+{
+ struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
sector_t last_block;
- int cluster, offset;
*phys = 0;
*mapped_blocks = 0;
@@ -321,31 +365,16 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
return 0;
}
- last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
- if (sector >= last_block) {
- if (!create)
+ if (!from_bmap) {
+ if (is_exceed_eof(inode, sector, &last_block, create))
return 0;
-
- /*
- * ->mmu_private can access on only allocation path.
- * (caller must hold ->i_mutex)
- */
- last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
- >> blocksize_bits;
+ } else {
+ last_block = inode->i_blocks >>
+ (inode->i_sb->s_blocksize_bits - 9);
if (sector >= last_block)
return 0;
}
- cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
- offset = sector & (sbi->sec_per_clus - 1);
- cluster = fat_bmap_cluster(inode, cluster);
- if (cluster < 0)
- return cluster;
- else if (cluster) {
- *phys = fat_clus_to_blknr(sbi, cluster) + offset;
- *mapped_blocks = sbi->sec_per_clus - offset;
- if (*mapped_blocks > last_block - sector)
- *mapped_blocks = last_block - sector;
- }
- return 0;
+ return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+ phys);
}
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 8b2127ffb226..7def96caec5f 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -91,7 +91,7 @@ next:
*bh = NULL;
iblock = *pos >> sb->s_blocksize_bits;
- err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0);
+ err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false);
if (err || !phys)
return -1; /* beyond EOF or error */
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index be5e15323bab..e6b764a17a9c 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -87,7 +87,7 @@ struct msdos_sb_info {
unsigned int vol_id; /*volume ID*/
int fatent_shift;
- struct fatent_operations *fatent_ops;
+ const struct fatent_operations *fatent_ops;
struct inode *fat_inode;
struct inode *fsinfo_inode;
@@ -285,8 +285,11 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
extern void fat_cache_inval_inode(struct inode *inode);
extern int fat_get_cluster(struct inode *inode, int cluster,
int *fclus, int *dclus);
+extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+ sector_t last_block,
+ unsigned long *mapped_blocks, sector_t *bmap);
extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
- unsigned long *mapped_blocks, int create);
+ unsigned long *mapped_blocks, int create, bool from_bmap);
/* fat/dir.c */
extern const struct file_operations fat_dir_operations;
@@ -384,6 +387,7 @@ static inline unsigned long fat_dir_hash(int logstart)
{
return hash_32(logstart, FAT_HASH_BITS);
}
+extern int fat_add_cluster(struct inode *inode);
/* fat/misc.c */
extern __printf(3, 4) __cold
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 8226557130a2..1d9a8c4e9de0 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -99,7 +99,7 @@ err:
static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent,
int offset, sector_t blocknr)
{
- struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+ const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
WARN_ON(blocknr < MSDOS_SB(sb)->fat_start);
fatent->fat_inode = MSDOS_SB(sb)->fat_inode;
@@ -246,7 +246,7 @@ static int fat32_ent_next(struct fat_entry *fatent)
return 0;
}
-static struct fatent_operations fat12_ops = {
+static const struct fatent_operations fat12_ops = {
.ent_blocknr = fat12_ent_blocknr,
.ent_set_ptr = fat12_ent_set_ptr,
.ent_bread = fat12_ent_bread,
@@ -255,7 +255,7 @@ static struct fatent_operations fat12_ops = {
.ent_next = fat12_ent_next,
};
-static struct fatent_operations fat16_ops = {
+static const struct fatent_operations fat16_ops = {
.ent_blocknr = fat_ent_blocknr,
.ent_set_ptr = fat16_ent_set_ptr,
.ent_bread = fat_ent_bread,
@@ -264,7 +264,7 @@ static struct fatent_operations fat16_ops = {
.ent_next = fat16_ent_next,
};
-static struct fatent_operations fat32_ops = {
+static const struct fatent_operations fat32_ops = {
.ent_blocknr = fat_ent_blocknr,
.ent_set_ptr = fat32_ent_set_ptr,
.ent_bread = fat_ent_bread,
@@ -320,7 +320,7 @@ static inline int fat_ent_update_ptr(struct super_block *sb,
int offset, sector_t blocknr)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
- struct fatent_operations *ops = sbi->fatent_ops;
+ const struct fatent_operations *ops = sbi->fatent_ops;
struct buffer_head **bhs = fatent->bhs;
/* Is this fatent's blocks including this entry? */
@@ -349,7 +349,7 @@ int fat_ent_read(struct inode *inode, struct fat_entry *fatent, int entry)
{
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
- struct fatent_operations *ops = sbi->fatent_ops;
+ const struct fatent_operations *ops = sbi->fatent_ops;
int err, offset;
sector_t blocknr;
@@ -407,7 +407,7 @@ int fat_ent_write(struct inode *inode, struct fat_entry *fatent,
int new, int wait)
{
struct super_block *sb = inode->i_sb;
- struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+ const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
int err;
ops->ent_put(fatent, new);
@@ -432,7 +432,7 @@ static inline int fat_ent_next(struct msdos_sb_info *sbi,
static inline int fat_ent_read_block(struct super_block *sb,
struct fat_entry *fatent)
{
- struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+ const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
sector_t blocknr;
int offset;
@@ -463,7 +463,7 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster)
{
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
- struct fatent_operations *ops = sbi->fatent_ops;
+ const struct fatent_operations *ops = sbi->fatent_ops;
struct fat_entry fatent, prev_ent;
struct buffer_head *bhs[MAX_BUF_PER_PAGE];
int i, count, err, nr_bhs, idx_clus;
@@ -551,7 +551,7 @@ int fat_free_clusters(struct inode *inode, int cluster)
{
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
- struct fatent_operations *ops = sbi->fatent_ops;
+ const struct fatent_operations *ops = sbi->fatent_ops;
struct fat_entry fatent;
struct buffer_head *bhs[MAX_BUF_PER_PAGE];
int i, err, nr_bhs;
@@ -636,7 +636,7 @@ EXPORT_SYMBOL_GPL(fat_free_clusters);
static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent,
unsigned long reada_blocks)
{
- struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
+ const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops;
sector_t blocknr;
int i, offset;
@@ -649,7 +649,7 @@ static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent,
int fat_count_free_clusters(struct super_block *sb)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
- struct fatent_operations *ops = sbi->fatent_ops;
+ const struct fatent_operations *ops = sbi->fatent_ops;
struct fat_entry fatent;
unsigned long reada_blocks, reada_mask, cur_block;
int err = 0, free;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a08f1039909a..43d3475da83a 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -14,8 +14,12 @@
#include <linux/backing-dev.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
+#include <linux/falloc.h>
#include "fat.h"
+static long fat_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len);
+
static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
{
u32 attr;
@@ -177,6 +181,7 @@ const struct file_operations fat_file_operations = {
#endif
.fsync = fat_file_fsync,
.splice_read = generic_file_splice_read,
+ .fallocate = fat_fallocate,
};
static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -215,6 +220,62 @@ out:
return err;
}
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len)
+{
+ int nr_cluster; /* Number of clusters to be allocated */
+ loff_t mm_bytes; /* Number of bytes to be allocated for file */
+ loff_t ondisksize; /* block aligned on-disk size in bytes*/
+ struct inode *inode = file->f_mapping->host;
+ struct super_block *sb = inode->i_sb;
+ struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ int err = 0;
+
+ /* No support for hole punch or other fallocate flags. */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ return -EOPNOTSUPP;
+
+ /* No support for dir */
+ if (!S_ISREG(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ mutex_lock(&inode->i_mutex);
+ if (mode & FALLOC_FL_KEEP_SIZE) {
+ ondisksize = inode->i_blocks << 9;
+ if ((offset + len) <= ondisksize)
+ goto error;
+
+ /* First compute the number of clusters to be allocated */
+ mm_bytes = offset + len - ondisksize;
+ nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+ sbi->cluster_bits;
+
+ /* Start the allocation.We are not zeroing out the clusters */
+ while (nr_cluster-- > 0) {
+ err = fat_add_cluster(inode);
+ if (err)
+ goto error;
+ }
+ } else {
+ if ((offset + len) <= i_size_read(inode))
+ goto error;
+
+ /* This is just an expanding truncate */
+ err = fat_cont_expand(inode, (offset + len));
+ }
+
+error:
+ mutex_unlock(&inode->i_mutex);
+ return err;
+}
+
/* Free all clusters after the skip'th cluster. */
static int fat_free(struct inode *inode, int skip)
{
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 6aece96df19f..a5599052116c 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -93,7 +93,7 @@ static struct fat_floppy_defaults {
},
};
-static int fat_add_cluster(struct inode *inode)
+int fat_add_cluster(struct inode *inode)
{
int err, cluster;
@@ -115,10 +115,10 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
unsigned long mapped_blocks;
- sector_t phys;
+ sector_t phys, last_block;
int err, offset;
- err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+ err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
if (err)
return err;
if (phys) {
@@ -135,8 +135,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
return -EIO;
}
+ last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9);
offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
- if (!offset) {
+ /*
+ * allocate a cluster according to the following.
+ * 1) no more available blocks
+ * 2) not part of fallocate region
+ */
+ if (!offset && !(iblock < last_block)) {
/* TODO: multiple cluster allocation would be desirable. */
err = fat_add_cluster(inode);
if (err)
@@ -148,7 +154,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
*max_blocks = min(mapped_blocks, *max_blocks);
MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;
- err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+ err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
if (err)
return err;
@@ -273,13 +279,38 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
return ret;
}
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ struct super_block *sb = inode->i_sb;
+ unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+ int err;
+ sector_t bmap;
+ unsigned long mapped_blocks;
+
+ BUG_ON(create != 0);
+
+ err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true);
+ if (err)
+ return err;
+
+ if (bmap) {
+ map_bh(bh_result, sb, bmap);
+ max_blocks = min(mapped_blocks, max_blocks);
+ }
+
+ bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+
+ return 0;
+}
+
static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
{
sector_t blocknr;
/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
down_read(&MSDOS_I(mapping->host)->truncate_lock);
- blocknr = generic_block_bmap(mapping, block, fat_get_block);
+ blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
up_read(&MSDOS_I(mapping->host)->truncate_lock);
return blocknr;
@@ -449,6 +480,24 @@ static int fat_calc_dir_size(struct inode *inode)
return 0;
}
+static int fat_validate_dir(struct inode *dir)
+{
+ struct super_block *sb = dir->i_sb;
+
+ if (dir->i_nlink < 2) {
+ /* Directory should have "."/".." entries at least. */
+ fat_fs_error(sb, "corrupted directory (invalid entries)");
+ return -EIO;
+ }
+ if (MSDOS_I(dir)->i_start == 0 ||
+ MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) {
+ /* Directory should point valid cluster. */
+ fat_fs_error(sb, "corrupted directory (invalid i_start)");
+ return -EIO;
+ }
+ return 0;
+}
+
/* doesn't deal with root inode */
int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
@@ -475,6 +524,10 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
MSDOS_I(inode)->mmu_private = inode->i_size;
set_nlink(inode, fat_subdirs(inode));
+
+ error = fat_validate_dir(inode);
+ if (error < 0)
+ return error;
} else { /* not a directory */
inode->i_generation |= 1;
inode->i_mode = fat_make_mode(sbi, de->attr,
@@ -553,13 +606,43 @@ out:
EXPORT_SYMBOL_GPL(fat_build_inode);
+static int __fat_write_inode(struct inode *inode, int wait);
+
+static void fat_free_eofblocks(struct inode *inode)
+{
+ /* Release unwritten fallocated blocks on inode eviction. */
+ if ((inode->i_blocks << 9) >
+ round_up(MSDOS_I(inode)->mmu_private,
+ MSDOS_SB(inode->i_sb)->cluster_size)) {
+ int err;
+
+ fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+ /* Fallocate results in updating the i_start/iogstart
+ * for the zero byte file. So, make it return to
+ * original state during evict and commit it to avoid
+ * any corruption on the next access to the cluster
+ * chain for the file.
+ */
+ err = __fat_write_inode(inode, inode_needs_sync(inode));
+ if (err) {
+ fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+ "update on disk inode for unused "
+ "fallocated blocks, inode could be "
+ "corrupted. Please run fsck");
+ }
+
+ }
+}
+
static void fat_evict_inode(struct inode *inode)
{
truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
fat_truncate_blocks(inode, 0);
- }
+ } else
+ fat_free_eofblocks(inode);
+
invalidate_inode_buffers(inode);
clear_inode(inode);
fat_cache_inval_inode(inode);
@@ -1146,7 +1229,12 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
case Opt_time_offset:
if (match_int(&args[0], &option))
return -EINVAL;
- if (option < -12 * 60 || option > 12 * 60)
+ /*
+ * GMT+-12 zones may have DST corrections so at least
+ * 13 hours difference is needed. Make the limit 24
+ * just in case someone invents something unusual.
+ */
+ if (option < -24 * 60 || option > 24 * 60)
return -EINVAL;
opts->tz_set = 1;
opts->time_offset = option;
diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c
index db458ee3a546..1eb5d415d434 100644
--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -214,7 +214,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str)
{
struct super_block *sb;
struct hfs_find_data fd;
- struct list_head *pos;
+ struct hfs_readdir_data *rd;
int res, type;
hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
@@ -240,9 +240,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str)
}
}
- list_for_each(pos, &HFS_I(dir)->open_dir_list) {
- struct hfs_readdir_data *rd =
- list_entry(pos, struct hfs_readdir_data, list);
+ list_for_each_entry(rd, &HFS_I(dir)->open_dir_list, list) {
if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
rd->file->f_pos--;
}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index a4cbdf9824c7..d250604f985a 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -16,6 +16,7 @@
#include <linux/slab.h>
#include <linux/parser.h>
#include <linux/module.h>
+#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d73291f5f0fc..b6c00ce0e29e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
state = *get_task_state(task);
vsize = eip = esp = 0;
- permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+ permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2cf5d7e37375..4f764c2ac1a5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+ struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
@@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
wchan = get_wchan(task);
- if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname))
+ if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+ && !lookup_symbol_name(wchan, symname))
seq_printf(m, "%s", symname);
else
seq_putc(m, '0');
@@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task)
int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (err)
return err;
- if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
mutex_unlock(&task->signal->cred_guard_mutex);
return -EPERM;
}
@@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
put_task_struct(task);
}
return allowed;
@@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
return true;
if (in_group_p(pid->pid_gid))
return true;
- return ptrace_may_access(task, PTRACE_MODE_READ);
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
@@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
struct mm_struct *mm = ERR_PTR(-ESRCH);
if (task) {
- mm = mm_access(task, mode);
+ mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
put_task_struct(task);
if (!IS_ERR_OR_NULL(mm)) {
@@ -952,6 +953,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
unsigned long src = *ppos;
int ret = 0;
struct mm_struct *mm = file->private_data;
+ unsigned long env_start, env_end;
if (!mm)
return 0;
@@ -963,19 +965,25 @@ static ssize_t environ_read(struct file *file, char __user *buf,
ret = 0;
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+
+ down_read(&mm->mmap_sem);
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
while (count > 0) {
size_t this_len, max_len;
int retval;
- if (src >= (mm->env_end - mm->env_start))
+ if (src >= (env_end - env_start))
break;
- this_len = mm->env_end - (mm->env_start + src);
+ this_len = env_end - (env_start + src);
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (mm->env_start + src),
+ retval = access_remote_vm(mm, (env_start + src),
page, this_len, 0);
if (retval <= 0) {
@@ -1860,7 +1868,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
if (!task)
goto out_notask;
- mm = mm_access(task, PTRACE_MODE_READ);
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm))
goto out;
@@ -2013,7 +2021,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
goto out;
result = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
result = -ENOENT;
@@ -2066,7 +2074,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
goto out;
ret = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
ret = 0;
@@ -2533,7 +2541,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
if (result)
return result;
- if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
result = -EACCES;
goto out_unlock;
}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 1dece8781f91..276f12431dbf 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -46,7 +46,7 @@ static const char *proc_ns_get_link(struct dentry *dentry,
if (!task)
return error;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
nd_jump_link(&ns_path);
@@ -67,7 +67,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (!task)
return res;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
res = readlink_copy(buffer, buflen, name);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 65a1b6c69c11..71ffc91060f6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -468,7 +468,7 @@ struct mem_size_stats {
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty)
{
- int i, nr = compound ? HPAGE_PMD_NR : 1;
+ int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
if (PageAnon(page))