s390/ism: fix receive message buffer allocation

Since [1], dma_alloc_coherent() does not accept requests for GFP_COMP
anymore, even on archs that may be able to fulfill this. Functionality that
relied on the receive buffer being a compound page broke at that point:
The SMC-D protocol, that utilizes the ism device driver, passes receive
buffers to the splice processor in a struct splice_pipe_desc with a
single entry list of struct pages. As the buffer is no longer a compound
page, the splice processor now rejects requests to handle more than a
page worth of data.

Replace dma_alloc_coherent() and allocate a buffer with folio_alloc and
create a DMA map for it with dma_map_page(). Since only receive buffers
on ISM devices use DMA, qualify the mapping as FROM_DEVICE.
Since ISM devices are available on arch s390, only and on that arch all
DMA is coherent, there is no need to introduce and export some kind of
dma_sync_to_cpu() method to be called by the SMC-D protocol layer.

Analogously, replace dma_free_coherent by a two step dma_unmap_page,
then folio_put to free the receive buffer.

[1] https://lore.kernel.org/all/20221113163535.884299-1-hch@lst.de/

Fixes: c08004e ("s390/ism: don't pass bogus GFP_ flags to dma_alloc_coherent")
Signed-off-by: Gerd Bayer <gbayer@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: Gerd Bayer

drivers/s390/net/ism_drv.c

@@ -14,6 +14,8 @@
 #include <linux/err.h>
 #include <linux/ctype.h>
 #include <linux/processor.h>
+#include <linux/dma-mapping.h>
+#include <linux/mm.h>
 
 #include "ism.h"
 
@@ -292,13 +294,15 @@ static int ism_read_local_gid(struct ism_dev *ism)
 static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 {
 	clear_bit(dmb->sba_idx, ism->sba_bitmap);
-	dma_free_coherent(&ism->pdev->dev, dmb->dmb_len,
-			  dmb->cpu_addr, dmb->dma_addr);
+	dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len,
+		       DMA_FROM_DEVICE);
+	folio_put(virt_to_folio(dmb->cpu_addr));
 }
 
 static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 {
 	unsigned long bit;
+	int rc;
 
 	if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev))
 		return -EINVAL;
@@ -315,14 +319,30 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 	    test_and_set_bit(dmb->sba_idx, ism->sba_bitmap))
 		return -EINVAL;
 
-	dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len,
-					   &dmb->dma_addr,
-					   GFP_KERNEL | __GFP_NOWARN |
-					   __GFP_NOMEMALLOC | __GFP_NORETRY);
-	if (!dmb->cpu_addr)
-		clear_bit(dmb->sba_idx, ism->sba_bitmap);
+	dmb->cpu_addr =
+		folio_address(folio_alloc(GFP_KERNEL | __GFP_NOWARN |
+					  __GFP_NOMEMALLOC | __GFP_NORETRY,
+					  get_order(dmb->dmb_len)));
 
-	return dmb->cpu_addr ? 0 : -ENOMEM;
+	if (!dmb->cpu_addr) {
+		rc = -ENOMEM;
+		goto out_bit;
+	}
+	dmb->dma_addr = dma_map_page(&ism->pdev->dev,
+				     virt_to_page(dmb->cpu_addr), 0,
+				     dmb->dmb_len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) {
+		rc = -ENOMEM;
+		goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	kfree(dmb->cpu_addr);
+out_bit:
+	clear_bit(dmb->sba_idx, ism->sba_bitmap);
+	return rc;
 }
 
 int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb,