Commit ea5c58e7 authored by Eric Biggers's avatar Eric Biggers Committed by Linus Torvalds

vfs: clear remainder of 'full_fds_bits' in dup_fd()

This fixes a bug from commit f3f86e33 ("vfs: Fix pathological
performance case for __alloc_fd()").

v2: refactor to share fd bitmap copying code
Signed-off-by: default avatarEric Biggers <ebiggers3@gmail.com>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 2c302e7e
......@@ -60,8 +60,31 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
/*
* Expand the fdset in the files_struct. Called with the files spinlock
* held for write.
* Copy 'count' fd bits from the old table to the new table and clear the extra
* space if any. This does not copy the file pointers. Called with the files
* spinlock held for write.
*/
static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
unsigned int count)
{
unsigned int cpy, set;
cpy = count / BITS_PER_BYTE;
set = (nfdt->max_fds - count) / BITS_PER_BYTE;
memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
memset((char *)nfdt->open_fds + cpy, 0, set);
memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
memset((char *)nfdt->close_on_exec + cpy, 0, set);
cpy = BITBIT_SIZE(count);
set = BITBIT_SIZE(nfdt->max_fds) - cpy;
memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
memset((char *)nfdt->full_fds_bits + cpy, 0, set);
}
/*
* Copy all file descriptors from the old table to the new, expanded table and
* clear the extra space. Called with the files spinlock held for write.
*/
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{
......@@ -72,19 +95,9 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
cpy = ofdt->max_fds * sizeof(struct file *);
set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)(nfdt->fd) + cpy, 0, set);
memset((char *)nfdt->fd + cpy, 0, set);
cpy = ofdt->max_fds / BITS_PER_BYTE;
set = (nfdt->max_fds - ofdt->max_fds) / BITS_PER_BYTE;
memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
memset((char *)(nfdt->open_fds) + cpy, 0, set);
memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
memset((char *)(nfdt->close_on_exec) + cpy, 0, set);
cpy = BITBIT_SIZE(ofdt->max_fds);
set = BITBIT_SIZE(nfdt->max_fds) - cpy;
memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
memset(cpy+(char *)nfdt->full_fds_bits, 0, set);
copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
}
static struct fdtable * alloc_fdtable(unsigned int nr)
......@@ -277,7 +290,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
int open_files, size, i;
int open_files, i;
struct fdtable *old_fdt, *new_fdt;
*errorp = -ENOMEM;
......@@ -334,13 +347,11 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
open_files = count_open_files(old_fdt);
}
copy_fd_bitmaps(new_fdt, old_fdt, open_files);
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
memcpy(new_fdt->full_fds_bits, old_fdt->full_fds_bits, BITBIT_SIZE(open_files));
for (i = open_files; i != 0; i--) {
struct file *f = *old_fds++;
if (f) {
......@@ -358,19 +369,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
}
spin_unlock(&oldf->file_lock);
/* compute the remainder to be cleared */
size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
/* This is long word aligned thus could use a optimized version */
memset(new_fds, 0, size);
if (new_fdt->max_fds > open_files) {
int left = (new_fdt->max_fds - open_files) / 8;
int start = open_files / BITS_PER_LONG;
memset(&new_fdt->open_fds[start], 0, left);
memset(&new_fdt->close_on_exec[start], 0, left);
}
/* clear the remainder */
memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *));
rcu_assign_pointer(newf->fdt, new_fdt);
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment