Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 64 insertions, 95 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4bf62b1afa3b..b2651bb6d2a3 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -408,27 +408,20 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 }
 EXPORT_SYMBOL(skb_kill_datagram);
 
-/**
- *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
- *	@skb: buffer to copy
- *	@offset: offset in the buffer to start copying from
- *	@to: iovec iterator to copy to
- *	@len: amount of data to copy from buffer to iovec
- */
-int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
-			   struct iov_iter *to, int len)
+int __skb_datagram_iter(const struct sk_buff *skb, int offset,
+			struct iov_iter *to, int len, bool fault_short,
+			size_t (*cb)(const void *, size_t, void *, struct iov_iter *),
+			void *data)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset, start_off = offset, n;
 	struct sk_buff *frag_iter;
 
-	trace_skb_copy_datagram_iovec(skb, len);
-
 	/* Copy header. */
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		n = copy_to_iter(skb->data + offset, copy, to);
+		n = cb(skb->data + offset, copy, data, to);
 		offset += n;
 		if (n != copy)
 			goto short_copy;
@@ -445,11 +438,14 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 
 		end = start + skb_frag_size(frag);
 		if ((copy = end - offset) > 0) {
+			struct page *page = skb_frag_page(frag);
+			u8 *vaddr = kmap(page);
+
 			if (copy > len)
 				copy = len;
-			n = copy_page_to_iter(skb_frag_page(frag),
-					      frag->page_offset + offset -
-					      start, copy, to);
+			n = cb(vaddr + frag->page_offset +
+				offset - start, copy, data, to);
+			kunmap(page);
 			offset += n;
 			if (n != copy)
 				goto short_copy;
@@ -468,8 +464,8 @@ int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
 		if ((copy = end - offset) > 0) {
 			if (copy > len)
 				copy = len;
-			if (skb_copy_datagram_iter(frag_iter, offset - start,
-						   to, copy))
+			if (__skb_datagram_iter(frag_iter, offset - start,
+						to, copy, fault_short, cb, data))
 				goto fault;
 			if ((len -= copy) == 0)
 				return 0;
@@ -490,11 +486,50 @@ fault:
 	return -EFAULT;
 
 short_copy:
-	if (iov_iter_count(to))
+	if (fault_short || iov_iter_count(to))
 		goto fault;
 
 	return 0;
 }
+
+/**
+ *	skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator
+ *          and update a hash.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *      @hash: hash request to update
+ */
+int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len,
+			   struct ahash_request *hash)
+{
+	return __skb_datagram_iter(skb, offset, to, len, true,
+			hash_and_copy_to_iter, hash);
+}
+EXPORT_SYMBOL(skb_copy_and_hash_datagram_iter);
+
+static size_t simple_copy_to_iter(const void *addr, size_t bytes,
+		void *data __always_unused, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
+/**
+ *	skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ */
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+			   struct iov_iter *to, int len)
+{
+	trace_skb_copy_datagram_iovec(skb, len);
+	return __skb_datagram_iter(skb, offset, to, len, false,
+			simple_copy_to_iter, NULL);
+}
 EXPORT_SYMBOL(skb_copy_datagram_iter);
 
 /**
@@ -645,87 +680,21 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
+/**
+ *	skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ *          and update a checksum.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: iovec iterator to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *      @csump: checksum pointer
+ */
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
-	int start = skb_headlen(skb);
-	int i, copy = start - offset, start_off = offset;
-	struct sk_buff *frag_iter;
-	int pos = 0;
-	int n;
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
-		offset += n;
-		if (n != copy)
-			goto fault;
-		if ((len -= copy) == 0)
-			return 0;
-		pos = copy;
-	}
-
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		if ((copy = end - offset) > 0) {
-			__wsum csum2 = 0;
-			struct page *page = skb_frag_page(frag);
-			u8  *vaddr = kmap(page);
-
-			if (copy > len)
-				copy = len;
-			n = csum_and_copy_to_iter(vaddr + frag->page_offset +
-						  offset - start, copy,
-						  &csum2, to);
-			kunmap(page);
-			offset += n;
-			if (n != copy)
-				goto fault;
-			*csump = csum_block_add(*csump, csum2, pos);
-			if (!(len -= copy))
-				return 0;
-			pos += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		if ((copy = end - offset) > 0) {
-			__wsum csum2 = 0;
-			if (copy > len)
-				copy = len;
-			if (skb_copy_and_csum_datagram(frag_iter,
-						       offset - start,
-						       to, copy,
-						       &csum2))
-				goto fault;
-			*csump = csum_block_add(*csump, csum2, pos);
-			if ((len -= copy) == 0)
-				return 0;
-			offset += copy;
-			pos += copy;
-		}
-		start = end;
-	}
-	if (!len)
-		return 0;
-
-fault:
-	iov_iter_revert(to, offset - start_off);
-	return -EFAULT;
+	return __skb_datagram_iter(skb, offset, to, len, true,
+			csum_and_copy_to_iter, csump);
 }
 
 /**