diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-04-12 14:49:50 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-04-12 14:49:50 -0700 |
commit | 5166701b368caea89d57b14bf41cf39e819dad51 (patch) | |
tree | c73b9d4860809e3afa9359be9d03ba2d8d98a18e /mm/iov_iter.c | |
parent | 0a7418f5f569512e98789c439198eed4b507cce3 (diff) | |
parent | a786c06d9f2719203c00b3d97b21f9a96980d0b5 (diff) |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs updates from Al Viro:
"The first vfs pile, with deep apologies for being very late in this
window.
Assorted cleanups and fixes, plus a large preparatory part of iov_iter
work. There's a lot more of that, but it'll probably go into the next
merge window - it *does* shape up nicely, removes a lot of
boilerplate, gets rid of locking inconsistencie between aio_write and
splice_write and I hope to get Kent's direct-io rewrite merged into
the same queue, but some of the stuff after this point is having
(mostly trivial) conflicts with the things already merged into
mainline and with some I want more testing.
This one passes LTP and xfstests without regressions, in addition to
usual beating. BTW, readahead02 in ltp syscalls testsuite has started
giving failures since "mm/readahead.c: fix readahead failure for
memoryless NUMA nodes and limit readahead pages" - might be a false
positive, might be a real regression..."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
missing bits of "splice: fix racy pipe->buffers uses"
cifs: fix the race in cifs_writev()
ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
kill generic_file_buffered_write()
ocfs2_file_aio_write(): switch to generic_perform_write()
ceph_aio_write(): switch to generic_perform_write()
xfs_file_buffered_aio_write(): switch to generic_perform_write()
export generic_perform_write(), start getting rid of generic_file_buffer_write()
generic_file_direct_write(): get rid of ppos argument
btrfs_file_aio_write(): get rid of ppos
kill the 5th argument of generic_file_buffered_write()
kill the 4th argument of __generic_file_aio_write()
lustre: don't open-code kernel_recvmsg()
ocfs2: don't open-code kernel_recvmsg()
drbd: don't open-code kernel_recvmsg()
constify blk_rq_map_user_iov() and friends
lustre: switch to kernel_sendmsg()
ocfs2: don't open-code kernel_sendmsg()
take iov_iter stuff to mm/iov_iter.c
process_vm_access: tidy up a bit
...
Diffstat (limited to 'mm/iov_iter.c')
-rw-r--r-- | mm/iov_iter.c | 224 |
1 files changed, 224 insertions, 0 deletions
diff --git a/mm/iov_iter.c b/mm/iov_iter.c new file mode 100644 index 000000000000..10e46cd721de --- /dev/null +++ b/mm/iov_iter.c @@ -0,0 +1,224 @@ +#include <linux/export.h> +#include <linux/uio.h> +#include <linux/pagemap.h> + +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_writeable(buf, copy)) { + kaddr = kmap_atomic(page); + from = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = from - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + from = kaddr + offset; + left = __copy_to_user(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + kunmap(page); +done: + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} +EXPORT_SYMBOL(copy_page_to_iter); + +static size_t __iovec_copy_from_user_inatomic(char *vaddr, + const struct iovec *iov, size_t base, size_t bytes) +{ + size_t copied = 0, left = 0; + + while (bytes) { + char __user *buf = iov->iov_base + base; + int copy = min(bytes, iov->iov_len - base); + + base = 0; + left = __copy_from_user_inatomic(vaddr, buf, copy); + copied += copy; + bytes -= copy; + vaddr += copy; + iov++; + + if (unlikely(left)) + break; + } + return copied - left; +} + +/* + * Copy as much as we can into the page and return the number of bytes which + * were successfully copied. If a fault is encountered then return the number of + * bytes which were copied. + */ +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap_atomic(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap_atomic(kaddr); + + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); + +/* + * This has the same sideeffects and return value as + * iov_iter_copy_from_user_atomic(). + * The difference is that it attempts to resolve faults. + * Page must not be locked. + */ +size_t iov_iter_copy_from_user(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap(page); + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user); + +void iov_iter_advance(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct iovec *iov = i->iov; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !iov->iov_len)) { + int copy; + + copy = min(bytes, iov->iov_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (iov->iov_len == base) { + iov++; + nr_segs--; + base = 0; + } + } + i->iov = iov; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} +EXPORT_SYMBOL(iov_iter_advance); + +/* + * Fault in the first iovec of the given iov_iter, to a maximum length + * of bytes. Returns 0 on success, or non-zero if the memory could not be + * accessed (ie. because it is an invalid address). + * + * writev-intensive code may want this to prefault several iovecs -- that + * would be possible (callers must not rely on the fact that _only_ the + * first iovec will be faulted with the current implementation). + */ +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) +{ + char __user *buf = i->iov->iov_base + i->iov_offset; + bytes = min(bytes, i->iov->iov_len - i->iov_offset); + return fault_in_pages_readable(buf, bytes); +} +EXPORT_SYMBOL(iov_iter_fault_in_readable); + +/* + * Return the count of just the current iov_iter segment. + */ +size_t iov_iter_single_seg_count(const struct iov_iter *i) +{ + const struct iovec *iov = i->iov; + if (i->nr_segs == 1) + return i->count; + else + return min(i->count, iov->iov_len - i->iov_offset); +} +EXPORT_SYMBOL(iov_iter_single_seg_count); |