diff options
Diffstat (limited to 'lib/iov_iter.c')
| -rw-r--r-- | lib/iov_iter.c | 969 |
1 files changed, 484 insertions, 485 deletions
diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e4dc809d1075..896760bad455 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <crypto/hash.h> #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> @@ -10,192 +9,83 @@ #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> -#include <net/checksum.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> +#include <linux/iov_iter.h> -/* covers ubuf and kbuf alike */ -#define iterate_buf(i, n, base, len, off, __p, STEP) { \ - size_t __maybe_unused off = 0; \ - len = n; \ - base = __p + i->iov_offset; \ - len -= (STEP); \ - i->iov_offset += len; \ - n = len; \ -} - -/* covers iovec and kvec alike */ -#define iterate_iovec(i, n, base, len, off, __p, STEP) { \ - size_t off = 0; \ - size_t skip = i->iov_offset; \ - do { \ - len = min(n, __p->iov_len - skip); \ - if (likely(len)) { \ - base = __p->iov_base + skip; \ - len -= (STEP); \ - off += len; \ - skip += len; \ - n -= len; \ - if (skip < __p->iov_len) \ - break; \ - } \ - __p++; \ - skip = 0; \ - } while (n); \ - i->iov_offset = skip; \ - n = off; \ -} - -#define iterate_bvec(i, n, base, len, off, p, STEP) { \ - size_t off = 0; \ - unsigned skip = i->iov_offset; \ - while (n) { \ - unsigned offset = p->bv_offset + skip; \ - unsigned left; \ - void *kaddr = kmap_local_page(p->bv_page + \ - offset / PAGE_SIZE); \ - base = kaddr + offset % PAGE_SIZE; \ - len = min(min(n, (size_t)(p->bv_len - skip)), \ - (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); \ - left = (STEP); \ - kunmap_local(kaddr); \ - len -= left; \ - off += len; \ - skip += len; \ - if (skip == p->bv_len) { \ - skip = 0; \ - p++; \ - } \ - n -= len; \ - if (left) \ - break; \ - } \ - i->iov_offset = skip; \ - n = off; \ -} - -#define iterate_xarray(i, n, base, len, __off, STEP) { \ - __label__ __out; \ - size_t __off = 0; \ - struct folio *folio; \ - loff_t start = i->xarray_start + i->iov_offset; \ - pgoff_t index = start / PAGE_SIZE; \ - XA_STATE(xas, i->xarray, index); \ - \ - len = PAGE_SIZE - offset_in_page(start); \ - rcu_read_lock(); \ - xas_for_each(&xas, folio, ULONG_MAX) { \ - unsigned left; \ - size_t offset; \ - if (xas_retry(&xas, folio)) \ - continue; \ - if (WARN_ON(xa_is_value(folio))) \ - break; \ - if (WARN_ON(folio_test_hugetlb(folio))) \ - break; \ - offset = offset_in_folio(folio, start + __off); \ - while (offset < folio_size(folio)) { \ - base = kmap_local_folio(folio, offset); \ - len = min(n, len); \ - left = (STEP); \ - kunmap_local(base); \ - len -= left; \ - __off += len; \ - n -= len; \ - if (left || n == 0) \ - goto __out; \ - offset += len; \ - len = PAGE_SIZE; \ - } \ - } \ -__out: \ - rcu_read_unlock(); \ - i->iov_offset += __off; \ - n = __off; \ -} - -#define __iterate_and_advance(i, n, base, len, off, I, K) { \ - if (unlikely(i->count < n)) \ - n = i->count; \ - if (likely(n)) { \ - if (likely(iter_is_ubuf(i))) { \ - void __user *base; \ - size_t len; \ - iterate_buf(i, n, base, len, off, \ - i->ubuf, (I)) \ - } else if (likely(iter_is_iovec(i))) { \ - const struct iovec *iov = iter_iov(i); \ - void __user *base; \ - size_t len; \ - iterate_iovec(i, n, base, len, off, \ - iov, (I)) \ - i->nr_segs -= iov - iter_iov(i); \ - i->__iov = iov; \ - } else if (iov_iter_is_bvec(i)) { \ - const struct bio_vec *bvec = i->bvec; \ - void *base; \ - size_t len; \ - iterate_bvec(i, n, base, len, off, \ - bvec, (K)) \ - i->nr_segs -= bvec - i->bvec; \ - i->bvec = bvec; \ - } else if (iov_iter_is_kvec(i)) { \ - const struct kvec *kvec = i->kvec; \ - void *base; \ - size_t len; \ - iterate_iovec(i, n, base, len, off, \ - kvec, (K)) \ - i->nr_segs -= kvec - i->kvec; \ - i->kvec = kvec; \ - } else if (iov_iter_is_xarray(i)) { \ - void *base; \ - size_t len; \ - iterate_xarray(i, n, base, len, off, \ - (K)) \ - } \ - i->count -= n; \ - } \ -} -#define iterate_and_advance(i, n, base, len, off, I, K) \ - __iterate_and_advance(i, n, base, len, off, I, ((void)(K),0)) - -static int copyout(void __user *to, const void *from, size_t n) +static __always_inline +size_t copy_to_user_iter(void __user *iter_to, size_t progress, + size_t len, void *from, void *priv2) { if (should_fail_usercopy()) - return n; - if (access_ok(to, n)) { - instrument_copy_to_user(to, from, n); - n = raw_copy_to_user(to, from, n); + return len; + if (access_ok(iter_to, len)) { + from += progress; + instrument_copy_to_user(iter_to, from, len); + len = raw_copy_to_user(iter_to, from, len); } - return n; + return len; } -static int copyout_nofault(void __user *to, const void *from, size_t n) +static __always_inline +size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress, + size_t len, void *from, void *priv2) { - long res; + ssize_t res; if (should_fail_usercopy()) - return n; - - res = copy_to_user_nofault(to, from, n); + return len; - return res < 0 ? n : res; + from += progress; + res = copy_to_user_nofault(iter_to, from, len); + return res < 0 ? len : res; } -static int copyin(void *to, const void __user *from, size_t n) +static __always_inline +size_t copy_from_user_iter(void __user *iter_from, size_t progress, + size_t len, void *to, void *priv2) { - size_t res = n; + size_t res = len; if (should_fail_usercopy()) - return n; - if (access_ok(from, n)) { - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); + return len; + if (can_do_masked_user_access()) { + iter_from = mask_user_address(iter_from); + } else { + if (!access_ok(iter_from, len)) + return res; + + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); } + to += progress; + instrument_copy_from_user_before(to, iter_from, len); + res = raw_copy_from_user(to, iter_from, len); + instrument_copy_from_user_after(to, iter_from, len, res); + return res; } +static __always_inline +size_t memcpy_to_iter(void *iter_to, size_t progress, + size_t len, void *from, void *priv2) +{ + memcpy(iter_to, from + progress, len); + return 0; +} + +static __always_inline +size_t memcpy_from_iter(void *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + memcpy(to + progress, iter_from, len); + return 0; +} + /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator @@ -288,9 +178,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, - .copy_mc = false, .nofault = false, - .user_backed = true, .data_source = direction, .__iov = iov, .nr_segs = nr_segs, @@ -300,36 +188,35 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_init); -static __wsum csum_and_memcpy(void *to, const void *from, size_t len, - __wsum sum, size_t off) -{ - __wsum next = csum_partial_copy_nocheck(from, to, len); - return csum_block_add(sum, next, off); -} - size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); - iterate_and_advance(i, bytes, base, len, off, - copyout(base, addr + off, len), - memcpy(base, addr + off, len) - ) - - return bytes; + return iterate_and_advance(i, bytes, (void *)addr, + copy_to_user_iter, memcpy_to_iter); } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC -static int copyout_mc(void __user *to, const void *from, size_t n) -{ - if (access_ok(to, n)) { - instrument_copy_to_user(to, from, n); - n = copy_mc_to_user((__force void *) to, from, n); +static __always_inline +size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress, + size_t len, void *from, void *priv2) +{ + if (access_ok(iter_to, len)) { + from += progress; + instrument_copy_to_user(iter_to, from, len); + len = copy_mc_to_user(iter_to, from, len); } - return n; + return len; +} + +static __always_inline +size_t memcpy_to_iter_mc(void *iter_to, size_t progress, + size_t len, void *from, void *priv2) +{ + return copy_mc_to_kernel(iter_to, from + progress, len); } /** @@ -362,22 +249,17 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) return 0; if (user_backed_iter(i)) might_fault(); - __iterate_and_advance(i, bytes, base, len, off, - copyout_mc(base, addr + off, len), - copy_mc_to_kernel(base, addr + off, len) - ) - - return bytes; + return iterate_and_advance(i, bytes, (void *)addr, + copy_to_user_iter_mc, memcpy_to_iter_mc); } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ -static void *memcpy_from_iter(struct iov_iter *i, void *to, const void *from, - size_t size) +static __always_inline +size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - if (iov_iter_is_copy_mc(i)) - return (void *)copy_mc_to_kernel(to, from, size); - return memcpy(to, from, size); + return iterate_and_advance(i, bytes, addr, + copy_from_user_iter, memcpy_from_iter); } size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) @@ -387,30 +269,44 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) if (user_backed_iter(i)) might_fault(); - iterate_and_advance(i, bytes, base, len, off, - copyin(addr + off, base, len), - memcpy_from_iter(i, addr + off, base, len) - ) - - return bytes; + return __copy_from_iter(addr, bytes, i); } EXPORT_SYMBOL(_copy_from_iter); +static __always_inline +size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + return __copy_from_user_inatomic_nocache(to + progress, iter_from, len); +} + size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; - iterate_and_advance(i, bytes, base, len, off, - __copy_from_user_inatomic_nocache(addr + off, base, len), - memcpy(addr + off, base, len) - ) - - return bytes; + return iterate_and_advance(i, bytes, addr, + copy_from_user_iter_nocache, + memcpy_from_iter); } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +static __always_inline +size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + return __copy_from_user_flushcache(to + progress, iter_from, len); +} + +static __always_inline +size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + memcpy_flushcache(to + progress, iter_from, len); + return 0; +} + /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address @@ -432,12 +328,9 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) if (WARN_ON_ONCE(!i->data_source)) return 0; - iterate_and_advance(i, bytes, base, len, off, - __copy_from_user_flushcache(addr + off, base, len), - memcpy_flushcache(addr + off, base, len) - ) - - return bytes; + return iterate_and_advance(i, bytes, addr, + copy_from_user_iter_flushcache, + memcpy_from_iter_flushcache); } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif @@ -509,10 +402,9 @@ size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t byte void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); - iterate_and_advance(i, n, base, len, off, - copyout_nofault(base, kaddr + offset + off, len), - memcpy(base, kaddr + offset + off, len) - ) + n = iterate_and_advance(i, n, kaddr + offset, + copy_to_user_iter_nofault, + memcpy_to_iter); kunmap_local(kaddr); res += n; bytes -= n; @@ -555,37 +447,57 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, } EXPORT_SYMBOL(copy_page_from_iter); -size_t iov_iter_zero(size_t bytes, struct iov_iter *i) +static __always_inline +size_t zero_to_user_iter(void __user *iter_to, size_t progress, + size_t len, void *priv, void *priv2) { - iterate_and_advance(i, bytes, base, len, count, - clear_user(base, len), - memset(base, 0, len) - ) + return clear_user(iter_to, len); +} - return bytes; +static __always_inline +size_t zero_to_iter(void *iter_to, size_t progress, + size_t len, void *priv, void *priv2) +{ + memset(iter_to, 0, len); + return 0; +} + +size_t iov_iter_zero(size_t bytes, struct iov_iter *i) +{ + return iterate_and_advance(i, bytes, NULL, + zero_to_user_iter, zero_to_iter); } EXPORT_SYMBOL(iov_iter_zero); -size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, - struct iov_iter *i) +size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) { - char *kaddr = kmap_atomic(page), *p = kaddr + offset; - if (!page_copy_sane(page, offset, bytes)) { - kunmap_atomic(kaddr); + size_t n, copied = 0; + + if (!page_copy_sane(&folio->page, offset, bytes)) return 0; - } - if (WARN_ON_ONCE(!i->data_source)) { - kunmap_atomic(kaddr); + if (WARN_ON_ONCE(!i->data_source)) return 0; - } - iterate_and_advance(i, bytes, base, len, off, - copyin(p + off, base, len), - memcpy_from_iter(i, p + off, base, len) - ) - kunmap_atomic(kaddr); - return bytes; + + do { + char *to = kmap_local_folio(folio, offset); + + n = bytes - copied; + if (folio_test_partial_kmap(folio) && + n > PAGE_SIZE - offset_in_page(offset)) + n = PAGE_SIZE - offset_in_page(offset); + + pagefault_disable(); + n = __copy_from_iter(to, n, i); + pagefault_enable(); + kunmap_local(to); + copied += n; + offset += n; + } while (copied != bytes && n > 0); + + return copied; } -EXPORT_SYMBOL(copy_page_from_iter_atomic); +EXPORT_SYMBOL(copy_folio_from_iter_atomic); static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { @@ -626,6 +538,39 @@ static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) i->__iov = iov; } +static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + if (!i->count) + return; + i->count -= size; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + + size += i->iov_offset; /* From beginning of current segment. */ + do { + size_t fsize = folioq_folio_size(folioq, slot); + + if (likely(size < fsize)) + break; + size -= fsize; + slot++; + if (slot >= folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } while (size); + + i->iov_offset = size; + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) @@ -638,12 +583,40 @@ void iov_iter_advance(struct iov_iter *i, size_t size) iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); + } else if (iov_iter_is_folioq(i)) { + iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); +static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + for (;;) { + size_t fsize; + + if (slot == 0) { + folioq = folioq->prev; + slot = folioq_nr_slots(folioq); + } + slot--; + + fsize = folioq_folio_size(folioq, slot); + if (unroll <= fsize) { + i->iov_offset = fsize - unroll; + break; + } + unroll -= fsize; + } + + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) @@ -675,6 +648,9 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) } unroll -= n; } + } else if (iov_iter_is_folioq(i)) { + i->iov_offset = 0; + iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { @@ -702,6 +678,9 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } + if (unlikely(iov_iter_is_folioq(i))) + return !i->count ? 0 : + umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); @@ -713,7 +692,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, - .copy_mc = false, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, @@ -730,7 +708,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, - .copy_mc = false, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, @@ -741,6 +718,36 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, EXPORT_SYMBOL(iov_iter_bvec); /** + * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @folioq: The starting point in the folio queue. + * @first_slot: The first slot in the folio queue to use + * @offset: The offset into the folio in the first slot to start at + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator to either draw data out of the pages attached to an + * inode or to inject data into those pages. The pages *must* be prevented + * from evaporation, either by taking a ref on them or locking them by the + * caller. + */ +void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, unsigned int first_slot, + unsigned int offset, size_t count) +{ + BUG_ON(direction & ~1); + *i = (struct iov_iter) { + .iter_type = ITER_FOLIOQ, + .data_source = direction, + .folioq = folioq, + .folioq_slot = first_slot, + .count = count, + .iov_offset = offset, + }; +} +EXPORT_SYMBOL(iov_iter_folio_queue); + +/** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. @@ -759,7 +766,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, - .copy_mc = false, .data_source = direction, .xarray = xarray, .xarray_start = start, @@ -783,7 +789,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, - .copy_mc = false, .data_source = false, .count = count, .iov_offset = 0 @@ -791,102 +796,14 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) } EXPORT_SYMBOL(iov_iter_discard); -static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask, - unsigned len_mask) -{ - size_t size = i->count; - size_t skip = i->iov_offset; - unsigned k; - - for (k = 0; k < i->nr_segs; k++, skip = 0) { - const struct iovec *iov = iter_iov(i) + k; - size_t len = iov->iov_len - skip; - - if (len > size) - len = size; - if (len & len_mask) - return false; - if ((unsigned long)(iov->iov_base + skip) & addr_mask) - return false; - - size -= len; - if (!size) - break; - } - return true; -} - -static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask, - unsigned len_mask) -{ - size_t size = i->count; - unsigned skip = i->iov_offset; - unsigned k; - - for (k = 0; k < i->nr_segs; k++, skip = 0) { - size_t len = i->bvec[k].bv_len - skip; - - if (len > size) - len = size; - if (len & len_mask) - return false; - if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask) - return false; - - size -= len; - if (!size) - break; - } - return true; -} - -/** - * iov_iter_is_aligned() - Check if the addresses and lengths of each segments - * are aligned to the parameters. - * - * @i: &struct iov_iter to restore - * @addr_mask: bit mask to check against the iov element's addresses - * @len_mask: bit mask to check against the iov element's lengths - * - * Return: false if any addresses or lengths intersect with the provided masks - */ -bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, - unsigned len_mask) -{ - if (likely(iter_is_ubuf(i))) { - if (i->count & len_mask) - return false; - if ((unsigned long)(i->ubuf + i->iov_offset) & addr_mask) - return false; - return true; - } - - if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) - return iov_iter_aligned_iovec(i, addr_mask, len_mask); - - if (iov_iter_is_bvec(i)) - return iov_iter_aligned_bvec(i, addr_mask, len_mask); - - if (iov_iter_is_xarray(i)) { - if (i->count & len_mask) - return false; - if ((i->xarray_start + i->iov_offset) & addr_mask) - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(iov_iter_is_aligned); - static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { + const struct iovec *iov = iter_iov(i); unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; - unsigned k; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - const struct iovec *iov = iter_iov(i) + k; + do { size_t len = iov->iov_len - skip; if (len) { res |= (unsigned long)iov->iov_base + skip; @@ -894,30 +811,31 @@ static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) len = size; res |= len; size -= len; - if (!size) - break; } - } + iov++; + skip = 0; + } while (size); return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { + const struct bio_vec *bvec = i->bvec; unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; - unsigned k; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - size_t len = i->bvec[k].bv_len - skip; - res |= (unsigned long)i->bvec[k].bv_offset + skip; + do { + size_t len = bvec->bv_len - skip; + res |= (unsigned long)bvec->bv_offset + skip; if (len > size) len = size; res |= len; + bvec++; size -= len; - if (!size) - break; - } + skip = 0; + } while (size); + return res; } @@ -937,6 +855,9 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); + /* With both xarray and folioq types, we're dealing with whole folios. */ + if (iov_iter_is_folioq(i)) + return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; @@ -989,26 +910,85 @@ static int want_pages_array(struct page ***res, size_t size, return count; } +static ssize_t iter_folioq_get_pages(struct iov_iter *iter, + struct page ***ppages, size_t maxsize, + unsigned maxpages, size_t *_start_offset) +{ + const struct folio_queue *folioq = iter->folioq; + struct page **pages; + unsigned int slot = iter->folioq_slot; + size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(iov_offset != 0)) + return -EIO; + } + + maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); + if (!maxpages) + return -ENOMEM; + *_start_offset = iov_offset & ~PAGE_MASK; + pages = *ppages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + count -= part; + iov_offset += part; + extracted += part; + + *pages = folio_page(folio, offset / PAGE_SIZE); + get_page(*pages); + pages++; + maxpages--; + } + + if (maxpages == 0 || extracted >= maxsize) + break; + + if (iov_offset >= fsize) { + iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + iter->count = count; + iter->iov_offset = iov_offset; + iter->folioq = folioq; + iter->folioq_slot = slot; + return extracted; +} + static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { XA_STATE(xas, xa, index); - struct page *page; + struct folio *folio; unsigned int ret = 0; rcu_read_lock(); - for (page = xas_load(&xas); page; page = xas_next(&xas)) { - if (xas_retry(&xas, page)) + for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) continue; - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) { + /* Has the folio moved or been split? */ + if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } - pages[ret] = find_subpage(page, xas.xa_index); - get_page(pages[ret]); + pages[ret] = folio_file_page(folio, xas.xa_index); + folio_get(folio); if (++ret == nr_pages) break; } @@ -1124,8 +1104,12 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, if (!n) return -ENOMEM; p = *pages; - for (int k = 0; k < n; k++) - get_page(p[k] = page + k); + for (int k = 0; k < n; k++) { + struct folio *folio = page_folio(page + k); + p[k] = page + k; + if (!folio_test_slab(folio)) + folio_get(folio); + } maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start); i->count -= maxsize; i->iov_offset += maxsize; @@ -1136,6 +1120,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, } return maxsize; } + if (iov_iter_is_folioq(i)) + return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; @@ -1168,78 +1154,6 @@ ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, } EXPORT_SYMBOL(iov_iter_get_pages_alloc2); -size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, - struct iov_iter *i) -{ - __wsum sum, next; - sum = *csum; - if (WARN_ON_ONCE(!i->data_source)) - return 0; - - iterate_and_advance(i, bytes, base, len, off, ({ - next = csum_and_copy_from_user(base, addr + off, len); - sum = csum_block_add(sum, next, off); - next ? 0 : len; - }), ({ - sum = csum_and_memcpy(addr + off, base, len, sum, off); - }) - ) - *csum = sum; - return bytes; -} -EXPORT_SYMBOL(csum_and_copy_from_iter); - -size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, - struct iov_iter *i) -{ - struct csum_state *csstate = _csstate; - __wsum sum, next; - - if (WARN_ON_ONCE(i->data_source)) - return 0; - if (unlikely(iov_iter_is_discard(i))) { - // can't use csum_memcpy() for that one - data is not copied - csstate->csum = csum_block_add(csstate->csum, - csum_partial(addr, bytes, 0), - csstate->off); - csstate->off += bytes; - return bytes; - } - - sum = csum_shift(csstate->csum, csstate->off); - iterate_and_advance(i, bytes, base, len, off, ({ - next = csum_and_copy_to_user(addr + off, base, len); - sum = csum_block_add(sum, next, off); - next ? 0 : len; - }), ({ - sum = csum_and_memcpy(base, addr + off, len, sum, off); - }) - ) - csstate->csum = csum_shift(sum, csstate->off); - csstate->off += bytes; - return bytes; -} -EXPORT_SYMBOL(csum_and_copy_to_iter); - -size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, - struct iov_iter *i) -{ -#ifdef CONFIG_CRYPTO_HASH - struct ahash_request *hash = hashp; - struct scatterlist sg; - size_t copied; - - copied = copy_to_iter(addr, bytes, i); - sg_init_one(&sg, addr, copied); - ahash_request_set_crypt(hash, &sg, NULL, copied); - crypto_ahash_update(hash); - return copied; -#else - return 0; -#endif -} -EXPORT_SYMBOL(hash_and_copy_to_iter); - static int iov_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; @@ -1292,6 +1206,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); + if (iov_iter_is_folioq(i)) { + unsigned offset = i->iov_offset % PAGE_SIZE; + int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); + return min(npages, maxpages); + } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); @@ -1318,11 +1237,12 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) EXPORT_SYMBOL(dup_iter); static __noclone int copy_compat_iovec_from_user(struct iovec *iov, - const struct iovec __user *uvec, unsigned long nr_segs) + const struct iovec __user *uvec, u32 nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; - int ret = -EFAULT, i; + int ret = -EFAULT; + u32 i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; @@ -1426,6 +1346,8 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec *iov = *iovp; ssize_t ret; + *iovp = NULL; + if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else @@ -1436,7 +1358,6 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; - *iovp = NULL; return i->count; } @@ -1521,19 +1442,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec, } EXPORT_SYMBOL(import_iovec); -int import_single_range(int rw, void __user *buf, size_t len, - struct iovec *iov, struct iov_iter *i) -{ - if (len > MAX_RW_COUNT) - len = MAX_RW_COUNT; - if (unlikely(!access_ok(buf, len))) - return -EFAULT; - - iov_iter_ubuf(i, rw, buf, len); - return 0; -} -EXPORT_SYMBOL(import_single_range); - int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) { if (len > MAX_RW_COUNT) @@ -1544,6 +1452,7 @@ int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) iov_iter_ubuf(i, rw, buf, len); return 0; } +EXPORT_SYMBOL_GPL(import_ubuf); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when @@ -1584,6 +1493,68 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) } /* + * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does + * not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + const struct folio_queue *folioq = i->folioq; + struct page **p; + unsigned int nr = 0; + size_t extracted = 0, offset, slot = i->folioq_slot; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(i->iov_offset != 0)) + return -EIO; + } + + offset = i->iov_offset & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + i->count -= part; + i->iov_offset += part; + extracted += part; + + p[nr++] = folio_page(folio, offset / PAGE_SIZE); + } + + if (nr >= maxpages || extracted >= maxsize) + break; + + if (i->iov_offset >= fsize) { + i->iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + i->folioq = folioq; + i->folioq_slot = slot; + return extracted; +} + +/* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. */ @@ -1593,11 +1564,11 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, iov_iter_extraction_t extraction_flags, size_t *offset0) { - struct page *page, **p; + struct page **p; + struct folio *folio; unsigned int nr = 0, offset; loff_t pos = i->xarray_start + i->iov_offset; - pgoff_t index = pos >> PAGE_SHIFT; - XA_STATE(xas, i->xarray, index); + XA_STATE(xas, i->xarray, pos >> PAGE_SHIFT); offset = pos & ~PAGE_MASK; *offset0 = offset; @@ -1608,17 +1579,17 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, p = *pages; rcu_read_lock(); - for (page = xas_load(&xas); page; page = xas_next(&xas)) { - if (xas_retry(&xas, page)) + for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { + if (xas_retry(&xas, folio)) continue; - /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) { + /* Has the folio moved or been split? */ + if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } - p[nr++] = find_subpage(page, xas.xa_index); + p[nr++] = folio_file_page(folio, xas.xa_index); if (nr == maxpages) break; } @@ -1630,8 +1601,8 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, } /* - * Extract a list of contiguous pages from an ITER_BVEC iterator. This does - * not get references on the pages, nor does it get a pin on them. + * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. + * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, @@ -1639,37 +1610,61 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, iov_iter_extraction_t extraction_flags, size_t *offset0) { - struct page **p, *page; - size_t skip = i->iov_offset, offset; - int k; + size_t skip = i->iov_offset, size = 0; + struct bvec_iter bi; + int k = 0; - for (;;) { - if (i->nr_segs == 0) - return 0; - maxsize = min(maxsize, i->bvec->bv_len - skip); - if (maxsize) - break; + if (i->nr_segs == 0) + return 0; + + if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } + bi.bi_idx = 0; + bi.bi_size = maxsize; + bi.bi_bvec_done = skip; + + maxpages = want_pages_array(pages, maxsize, skip, maxpages); + + while (bi.bi_size && bi.bi_idx < i->nr_segs) { + struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); + + /* + * The iov_iter_extract_pages interface only allows an offset + * into the first page. Break out of the loop if we see an + * offset into subsequent pages, the caller will have to call + * iov_iter_extract_pages again for the reminder. + */ + if (k) { + if (bv.bv_offset) + break; + } else { + *offset0 = bv.bv_offset; + } - skip += i->bvec->bv_offset; - page = i->bvec->bv_page + skip / PAGE_SIZE; - offset = skip % PAGE_SIZE; - *offset0 = offset; + (*pages)[k++] = bv.bv_page; + size += bv.bv_len; - maxpages = want_pages_array(pages, maxsize, offset, maxpages); - if (!maxpages) - return -ENOMEM; - p = *pages; - for (k = 0; k < maxpages; k++) - p[k] = page + k; + if (k >= maxpages) + break; - maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); - iov_iter_advance(i, maxsize); - return maxsize; + /* + * We are done when the end of the bvec doesn't align to a page + * boundary as that would create a hole in the returned space. + * The caller will handle this with another call to + * iov_iter_extract_pages. + */ + if (bv.bv_offset + bv.bv_len != PAGE_SIZE) + break; + + bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); + } + + iov_iter_advance(i, size); + return size; } /* @@ -1684,14 +1679,14 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, { struct page **p, *page; const void *kaddr; - size_t skip = i->iov_offset, offset, len; + size_t skip = i->iov_offset, offset, len, size; int k; for (;;) { if (i->nr_segs == 0) return 0; - maxsize = min(maxsize, i->kvec->iov_len - skip); - if (maxsize) + size = min(maxsize, i->kvec->iov_len - skip); + if (size) break; i->iov_offset = 0; i->nr_segs--; @@ -1703,13 +1698,13 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, offset = (unsigned long)kaddr & ~PAGE_MASK; *offset0 = offset; - maxpages = want_pages_array(pages, maxsize, offset, maxpages); + maxpages = want_pages_array(pages, size, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; kaddr -= offset; - len = offset + maxsize; + len = offset + size; for (k = 0; k < maxpages; k++) { size_t seg = min_t(size_t, len, PAGE_SIZE); @@ -1723,9 +1718,9 @@ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, kaddr += PAGE_SIZE; } - maxsize = min_t(size_t, maxsize, maxpages * PAGE_SIZE - offset); - iov_iter_advance(i, maxsize); - return maxsize; + size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); + iov_iter_advance(i, size); + return size; } /* @@ -1803,8 +1798,8 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * - * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are - * merely listed; no extra refs or pins are obtained. + * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the + * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: @@ -1839,6 +1834,10 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i, return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); + if (iov_iter_is_folioq(i)) + return iov_iter_extract_folioq_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, |