Release 4.16 lib/iov_iter.c
#include <linux/export.h>
#include <linux/bvec.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/splice.h>
#include <net/checksum.h>
#define PIPE_PARANOIA
/* for now */
#define iterate_iovec(i, n, __v, __p, skip, STEP) { \
size_t left; \
size_t wanted = n; \
__p = i->iov; \
__v.iov_len = min(n, __p->iov_len - skip); \
if (likely(__v.iov_len)) { \
__v.iov_base = __p->iov_base + skip; \
left = (STEP); \
__v.iov_len -= left; \
skip += __v.iov_len; \
n -= __v.iov_len; \
} else { \
left = 0; \
} \
while (unlikely(!left && n)) { \
__p++; \
__v.iov_len = min(n, __p->iov_len); \
if (unlikely(!__v.iov_len)) \
continue; \
__v.iov_base = __p->iov_base; \
left = (STEP); \
__v.iov_len -= left; \
skip = __v.iov_len; \
n -= __v.iov_len; \
} \
n = wanted - n; \
}
#define iterate_kvec(i, n, __v, __p, skip, STEP) { \
size_t wanted = n; \
__p = i->kvec; \
__v.iov_len = min(n, __p->iov_len - skip); \
if (likely(__v.iov_len)) { \
__v.iov_base = __p->iov_base + skip; \
(void)(STEP); \
skip += __v.iov_len; \
n -= __v.iov_len; \
} \
while (unlikely(n)) { \
__p++; \
__v.iov_len = min(n, __p->iov_len); \
if (unlikely(!__v.iov_len)) \
continue; \
__v.iov_base = __p->iov_base; \
(void)(STEP); \
skip = __v.iov_len; \
n -= __v.iov_len; \
} \
n = wanted; \
}
#define iterate_bvec(i, n, __v, __bi, skip, STEP) { \
struct bvec_iter __start; \
__start.bi_size = n; \
__start.bi_bvec_done = skip; \
__start.bi_idx = 0; \
for_each_bvec(__v, i->bvec, __bi, __start) { \
if (!__v.bv_len) \
continue; \
(void)(STEP); \
} \
}
#define iterate_all_kinds(i, n, v, I, B, K) { \
if (likely(n)) { \
size_t skip = i->iov_offset; \
if (unlikely(i->type & ITER_BVEC)) { \
struct bio_vec v; \
struct bvec_iter __bi; \
iterate_bvec(i, n, v, __bi, skip, (B)) \
} else if (unlikely(i->type & ITER_KVEC)) { \
const struct kvec *kvec; \
struct kvec v; \
iterate_kvec(i, n, v, kvec, skip, (K)) \
} else { \
const struct iovec *iov; \
struct iovec v; \
iterate_iovec(i, n, v, iov, skip, (I)) \
} \
} \
}
#define iterate_and_advance(i, n, v, I, B, K) { \
if (unlikely(i->count < n)) \
n = i->count; \
if (i->count) { \
size_t skip = i->iov_offset; \
if (unlikely(i->type & ITER_BVEC)) { \
const struct bio_vec *bvec = i->bvec; \
struct bio_vec v; \
struct bvec_iter __bi; \
iterate_bvec(i, n, v, __bi, skip, (B)) \
i->bvec = __bvec_iter_bvec(i->bvec, __bi); \
i->nr_segs -= i->bvec - bvec; \
skip = __bi.bi_bvec_done; \
} else if (unlikely(i->type & ITER_KVEC)) { \
const struct kvec *kvec; \
struct kvec v; \
iterate_kvec(i, n, v, kvec, skip, (K)) \
if (skip == kvec->iov_len) { \
kvec++; \
skip = 0; \
} \
i->nr_segs -= kvec - i->kvec; \
i->kvec = kvec; \
} else { \
const struct iovec *iov; \
struct iovec v; \
iterate_iovec(i, n, v, iov, skip, (I)) \
if (skip == iov->iov_len) { \
iov++; \
skip = 0; \
} \
i->nr_segs -= iov - i->iov; \
i->iov = iov; \
} \
i->count -= n; \
i->iov_offset = skip; \
} \
}
static int copyout(void __user *to, const void *from, size_t n)
{
if (access_ok(VERIFY_WRITE, to, n)) {
kasan_check_read(from, n);
n = raw_copy_to_user(to, from, n);
}
return n;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 53 | 100.00% | 1 | 100.00% |
Total | 53 | 100.00% | 1 | 100.00% |
static int copyin(void *to, const void __user *from, size_t n)
{
if (access_ok(VERIFY_READ, from, n)) {
kasan_check_write(to, n);
n = raw_copy_from_user(to, from, n);
}
return n;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 53 | 100.00% | 1 | 100.00% |
Total | 53 | 100.00% | 1 | 100.00% |
static size_t copy_page_to_iter_iovec(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;
might_fault();
wanted = bytes;
iov = i->iov;
skip = i->iov_offset;
buf = iov->iov_base + skip;
copy = min(bytes, iov->iov_len - skip);
if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) {
kaddr = kmap_atomic(page);
from = kaddr + offset;
/* first chunk, usually the only one */
left = copyout(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 = copyout(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 = copyout(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 = copyout(buf, from, copy);
copy -= left;
skip = copy;
from += copy;
bytes -= copy;
}
kunmap(page);
done:
if (skip == iov->iov_len) {
iov++;
skip = 0;
}
i->count -= wanted - bytes;
i->nr_segs -= iov - i->iov;
i->iov = iov;
i->iov_offset = skip;
return wanted - bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 416 | 94.76% | 4 | 66.67% |
Matthew Wilcox | 18 | 4.10% | 1 | 16.67% |
Mikulas Patocka | 5 | 1.14% | 1 | 16.67% |
Total | 439 | 100.00% | 6 | 100.00% |
static size_t copy_page_from_iter_iovec(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, *to;
if (unlikely(bytes > i->count))
bytes = i->count;
if (unlikely(!bytes))
return 0;
might_fault();
wanted = bytes;
iov = i->iov;
skip = i->iov_offset;
buf = iov->iov_base + skip;
copy = min(bytes, iov->iov_len - skip);
if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) {
kaddr = kmap_atomic(page);
to = kaddr + offset;
/* first chunk, usually the only one */
left = copyin(to, buf, copy);
copy -= left;
skip += copy;
to += copy;
bytes -= copy;
while (unlikely(!left && bytes)) {
iov++;
buf = iov->iov_base;
copy = min(bytes, iov->iov_len);
left = copyin(to, buf, copy);
copy -= left;
skip = copy;
to += copy;
bytes -= copy;
}
if (likely(!bytes)) {
kunmap_atomic(kaddr);
goto done;
}
offset = to - kaddr;
buf += copy;
kunmap_atomic(kaddr);
copy = min(bytes, iov->iov_len - skip);
}
/* Too bad - revert to non-atomic kmap */
kaddr = kmap(page);
to = kaddr + offset;
left = copyin(to, buf, copy);
copy -= left;
skip += copy;
to += copy;
bytes -= copy;
while (unlikely(!left && bytes)) {
iov++;
buf = iov->iov_base;
copy = min(bytes, iov->iov_len);
left = copyin(to, buf, copy);
copy -= left;
skip = copy;
to += copy;
bytes -= copy;
}
kunmap(page);
done:
if (skip == iov->iov_len) {
iov++;
skip = 0;
}
i->count -= wanted - bytes;
i->nr_segs -= iov - i->iov;
i->iov = iov;
i->iov_offset = skip;
return wanted - bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Matthew Wilcox | 361 | 82.23% | 1 | 25.00% |
Al Viro | 73 | 16.63% | 2 | 50.00% |
Mikulas Patocka | 5 | 1.14% | 1 | 25.00% |
Total | 439 | 100.00% | 4 | 100.00% |
#ifdef PIPE_PARANOIA
static bool sanity(const struct iov_iter *i)
{
struct pipe_inode_info *pipe = i->pipe;
int idx = i->idx;
int next = pipe->curbuf + pipe->nrbufs;
if (i->iov_offset) {
struct pipe_buffer *p;
if (unlikely(!pipe->nrbufs))
goto Bad; // pipe must be non-empty
if (unlikely(idx != ((next - 1) & (pipe->buffers - 1))))
goto Bad; // must be at the last buffer...
p = &pipe->bufs[idx];
if (unlikely(p->offset + p->len != i->iov_offset))
goto Bad; // ... at the end of segment
} else {
if (idx != (next & (pipe->buffers - 1)))
goto Bad; // must be right after the last buffer
}
return true;
Bad:
printk(KERN_ERR "idx = %d, offset = %zd\n", i->idx, i->iov_offset);
printk(KERN_ERR "curbuf = %d, nrbufs = %d, buffers = %d\n",
pipe->curbuf, pipe->nrbufs, pipe->buffers);
for (idx = 0; idx < pipe->buffers; idx++)
printk(KERN_ERR "[%p %p %d %d]\n",
pipe->bufs[idx].ops,
pipe->bufs[idx].page,
pipe->bufs[idx].offset,
pipe->bufs[idx].len);
WARN_ON(1);
return false;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 218 | 87.55% | 2 | 66.67% |
Anton Altaparmakov | 31 | 12.45% | 1 | 33.33% |
Total | 249 | 100.00% | 3 | 100.00% |
#else
#define sanity(i) true
#endif
static inline int next_idx(int idx, struct pipe_inode_info *pipe)
{
return (idx + 1) & (pipe->buffers - 1);
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 30 | 100.00% | 3 | 100.00% |
Total | 30 | 100.00% | 3 | 100.00% |
static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
struct pipe_inode_info *pipe = i->pipe;
struct pipe_buffer *buf;
size_t off;
int idx;
if (unlikely(bytes > i->count))
bytes = i->count;
if (unlikely(!bytes))
return 0;
if (!sanity(i))
return 0;
off = i->iov_offset;
idx = i->idx;
buf = &pipe->bufs[idx];
if (off) {
if (offset == off && buf->page == page) {
/* merge with the last one */
buf->len += bytes;
i->iov_offset += bytes;
goto out;
}
idx = next_idx(idx, pipe);
buf = &pipe->bufs[idx];
}
if (idx == pipe->curbuf && pipe->nrbufs)
return 0;
pipe->nrbufs++;
buf->ops = &page_cache_pipe_buf_ops;
get_page(buf->page = page);
buf->offset = offset;
buf->len = bytes;
i->iov_offset = offset + bytes;
i->idx = idx;
out:
i->count -= bytes;
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 231 | 100.00% | 2 | 100.00% |
Total | 231 | 100.00% | 2 | 100.00% |
/*
* Fault in one or more iovecs of the given iov_iter, to a maximum length of
* bytes. For each iovec, fault in each page that constitutes the iovec.
*
* Return 0 on success, or non-zero if the memory could not be accessed (i.e.
* because it is an invalid address).
*/
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
{
size_t skip = i->iov_offset;
const struct iovec *iov;
int err;
struct iovec v;
if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
iterate_iovec(i, bytes, v, iov, skip, ({
err = fault_in_pages_readable(v.iov_base, v.iov_len);
if (unlikely(err))
return err;
0;}))
}
return 0;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 68 | 98.55% | 2 | 66.67% |
Linus Torvalds | 1 | 1.45% | 1 | 33.33% |
Total | 69 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL(iov_iter_fault_in_readable);
void iov_iter_init(struct iov_iter *i, int direction,
const struct iovec *iov, unsigned long nr_segs,
size_t count)
{
/* It will get better. Eventually... */
if (uaccess_kernel()) {
direction |= ITER_KVEC;
i->type = direction;
i->kvec = (struct kvec *)iov;
} else {
i->type = direction;
i->iov = iov;
}
i->nr_segs = nr_segs;
i->iov_offset = 0;
i->count = count;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 88 | 100.00% | 2 | 100.00% |
Total | 88 | 100.00% | 2 | 100.00% |
EXPORT_SYMBOL(iov_iter_init);
static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len)
{
char *from = kmap_atomic(page);
memcpy(to, from + offset, len);
kunmap_atomic(from);
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 46 | 100.00% | 1 | 100.00% |
Total | 46 | 100.00% | 1 | 100.00% |
static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
{
char *to = kmap_atomic(page);
memcpy(to + offset, from, len);
kunmap_atomic(to);
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 47 | 100.00% | 1 | 100.00% |
Total | 47 | 100.00% | 1 | 100.00% |
static void memzero_page(struct page *page, size_t offset, size_t len)
{
char *addr = kmap_atomic(page);
memset(addr + offset, 0, len);
kunmap_atomic(addr);
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 42 | 100.00% | 1 | 100.00% |
Total | 42 | 100.00% | 1 | 100.00% |
static inline bool allocated(struct pipe_buffer *buf)
{
return buf->ops == &default_pipe_buf_ops;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 20 | 100.00% | 1 | 100.00% |
Total | 20 | 100.00% | 1 | 100.00% |
static inline void data_start(const struct iov_iter *i, int *idxp, size_t *offp)
{
size_t off = i->iov_offset;
int idx = i->idx;
if (off && (!allocated(&i->pipe->bufs[idx]) || off == PAGE_SIZE)) {
idx = next_idx(idx, i->pipe);
off = 0;
}
*idxp = idx;
*offp = off;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 86 | 100.00% | 1 | 100.00% |
Total | 86 | 100.00% | 1 | 100.00% |
static size_t push_pipe(struct iov_iter *i, size_t size,
int *idxp, size_t *offp)
{
struct pipe_inode_info *pipe = i->pipe;
size_t off;
int idx;
ssize_t left;
if (unlikely(size > i->count))
size = i->count;
if (unlikely(!size))
return 0;
left = size;
data_start(i, &idx, &off);
*idxp = idx;
*offp = off;
if (off) {
left -= PAGE_SIZE - off;
if (left <= 0) {
pipe->bufs[idx].len += size;
return size;
}
pipe->bufs[idx].len = PAGE_SIZE;
idx = next_idx(idx, pipe);
}
while (idx != pipe->curbuf || !pipe->nrbufs) {
struct page *page = alloc_page(GFP_USER);
if (!page)
break;
pipe->nrbufs++;
pipe->bufs[idx].ops = &default_pipe_buf_ops;
pipe->bufs[idx].page = page;
pipe->bufs[idx].offset = 0;
if (left <= PAGE_SIZE) {
pipe->bufs[idx].len = left;
return size;
}
pipe->bufs[idx].len = PAGE_SIZE;
left -= PAGE_SIZE;
idx = next_idx(idx, pipe);
}
return size - left;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 268 | 100.00% | 1 | 100.00% |
Total | 268 | 100.00% | 1 | 100.00% |
static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
struct iov_iter *i)
{
struct pipe_inode_info *pipe = i->pipe;
size_t n, off;
int idx;
if (!sanity(i))
return 0;
bytes = n = push_pipe(i, bytes, &idx, &off);
if (unlikely(!n))
return 0;
for ( ; n; idx = next_idx(idx, pipe), off = 0) {
size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
memcpy_to_page(pipe->bufs[idx].page, off, addr, chunk);
i->idx = idx;
i->iov_offset = off + chunk;
n -= chunk;
addr += chunk;
}
i->count -= bytes;
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 158 | 100.00% | 1 | 100.00% |
Total | 158 | 100.00% | 1 | 100.00% |
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
const char *from = addr;
if (unlikely(i->type & ITER_PIPE))
return copy_pipe_to_iter(addr, bytes, i);
if (iter_is_iovec(i))
might_fault();
iterate_and_advance(i, bytes, v,
copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
memcpy_to_page(v.bv_page, v.bv_offset,
(from += v.bv_len) - v.bv_len, v.bv_len),
memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len)
)
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 73 | 100.00% | 3 | 100.00% |
Total | 73 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL(_copy_to_iter);
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
if (unlikely(i->type & ITER_PIPE)) {
WARN_ON(1);
return 0;
}
if (iter_is_iovec(i))
might_fault();
iterate_and_advance(i, bytes, v,
copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len),
memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
v.bv_offset, v.bv_len),
memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
)
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 71 | 100.00% | 3 | 100.00% |
Total | 71 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL(_copy_from_iter);
bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
if (unlikely(i->type & ITER_PIPE)) {
WARN_ON(1);
return false;
}
if (unlikely(i->count < bytes))
return false;
if (iter_is_iovec(i))
might_fault();
iterate_all_kinds(i, bytes, v, ({
if (copyin((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len))
return false;
0;}),
memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
v.bv_offset, v.bv_len),
memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
)
iov_iter_advance(i, bytes);
return true;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 94 | 100.00% | 3 | 100.00% |
Total | 94 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL(_copy_from_iter_full);
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
if (unlikely(i->type & ITER_PIPE)) {
WARN_ON(1);
return 0;
}
iterate_and_advance(i, bytes, v,
__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len),
memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
v.bv_offset, v.bv_len),
memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
)
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Al Viro | 61 | 100.00% | 3 | 100.00% |
Total | 61 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL(_copy_from_iter_nocache);
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
if (unlikely(i->type & ITER_PIPE)) {
WARN_ON(1);
return 0;
}
iterate_and_advance(i, bytes, v,
__copy_from_user_flushcache((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len),
memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page,
v.bv_offset, v.bv_len),
memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base,
v.iov_len)
)
return bytes;
}
Contributors
Person | Tokens | Prop | Commits | CommitProp |
Dan J Williams | 60 | 98.36% | 1 | 50.00% |
Linus Torvalds | 1 | 1.64% | 1 | 50.00% |
Total | 61 | 100.00% | 2 | 100.00% |
EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache);
#endif
bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
if (unlikely(i->type & ITER_PIPE)) {
WARN_ON(1);
return false;
}
if (unlikely(i->count < bytes))
return false;
iterate_all_kinds(i, bytes, v