RDMA/siw: Convert siw_tx_hdt() to kmap_local_page()

kmap() is being deprecated and will break uses of device dax after PKS
protection is introduced.[1]

The use of kmap() in siw_tx_hdt() is all thread local therefore
kmap_local_page() is a sufficient replacement and will work with pgmap
protected pages when those are implemented.

siw_tx_hdt() tracks pages used in a page_array.  It uses that array to
unmap pages which were mapped on function exit.  Not all entries in the
array are mapped and this is tracked in kmap_mask.

kunmap_local() takes a mapped address rather than a page.  Alter
siw_unmap_pages() to take the iov array to reuse the iov_base address of
each mapping.  Use PAGE_MASK to get the proper address for kunmap_local().

kmap_local_page() mappings are tracked in a stack and must be unmapped in
the opposite order they were mapped in.  Because segments are mapped into
the page array in increasing index order, modify siw_unmap_pages() to
unmap pages in decreasing order.

Use kmap_local_page() instead of kmap() to map pages in the page_array.

[1] https://lore.kernel.org/lkml/20201009195033.3208459-59-ira.weiny@intel.com/

Link: https://lore.kernel.org/r/20210624174814.2822896-1-ira.weiny@intel.comSigned-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/sw/siw/siw_qp_tx.c

@@ -396,13 +396,20 @@ static int siw_0copy_tx(struct socket *s, struct page **page,
 
 #define MAX_TRAILER (MPA_CRC_SIZE + 4)
 
-static void siw_unmap_pages(struct page **pp, unsigned long kmap_mask)
+static void siw_unmap_pages(struct kvec *iov, unsigned long kmap_mask, int len)
 {
-	while (kmap_mask) {
-		if (kmap_mask & BIT(0))
-			kunmap(*pp);
-		pp++;
-		kmap_mask >>= 1;
+	int i;
+
+	/*
+	 * Work backwards through the array to honor the kmap_local_page()
+	 * ordering requirements.
+	 */
+	for (i = (len-1); i >= 0; i--) {
+		if (kmap_mask & BIT(i)) {
+			unsigned long addr = (unsigned long)iov[i].iov_base;
+
+			kunmap_local((void *)(addr & PAGE_MASK));
+		}
 	}
 }
 
@@ -498,7 +505,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					p = siw_get_upage(mem->umem,
 							  sge->laddr + sge_off);
 				if (unlikely(!p)) {
-					siw_unmap_pages(page_array, kmap_mask);
+					siw_unmap_pages(iov, kmap_mask, seg);
 					wqe->processed -= c_tx->bytes_unsent;
 					rv = -EFAULT;
 					goto done_crc;
@@ -506,11 +513,12 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 				page_array[seg] = p;
 
 				if (!c_tx->use_sendpage) {
-					iov[seg].iov_base = kmap(p) + fp_off;
-					iov[seg].iov_len = plen;
+					void *kaddr = kmap_local_page(p);
 
 					/* Remember for later kunmap() */
 					kmap_mask |= BIT(seg);
+					iov[seg].iov_base = kaddr + fp_off;
+					iov[seg].iov_len = plen;
 
 					if (do_crc)
 						crypto_shash_update(
@@ -542,7 +550,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 
 			if (++seg > (int)MAX_ARRAY) {
 				siw_dbg_qp(tx_qp(c_tx), "to many fragments\n");
-				siw_unmap_pages(page_array, kmap_mask);
+				siw_unmap_pages(iov, kmap_mask, seg-1);
 				wqe->processed -= c_tx->bytes_unsent;
 				rv = -EMSGSIZE;
 				goto done_crc;
@@ -593,7 +601,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 	} else {
 		rv = kernel_sendmsg(s, &msg, iov, seg + 1,
 				    hdr_len + data_len + trl_len);
-		siw_unmap_pages(page_array, kmap_mask);
+		siw_unmap_pages(iov, kmap_mask, seg);
 	}
 	if (rv < (int)hdr_len) {
 		/* Not even complete hdr pushed or negative rv */